Ci testsg

2026-02-03 03:02:38 -05:00 · 2024-06-13 23:34:11 +02:00
202 changed files with 1574 additions and 4916 deletions
--- a/.github/check_and_update.py
+++ b/.github/check_and_update.py
@@ -1,79 +0,0 @@
-import hashlib
-from huggingface_hub import hf_hub_download, get_paths_info
-import requests
-import sys
-import os
-
-uri = sys.argv[0]
-file_name = uri.split('/')[-1]
-
-# Function to parse the URI and determine download method
-def parse_uri(uri):
-    if uri.startswith('huggingface://'):
-        repo_id = uri.split('://')[1]
-        return 'huggingface', repo_id.rsplit('/', 1)[0]
-    elif 'huggingface.co' in uri:
-        parts = uri.split('/resolve/')
-        if len(parts) > 1:
-            repo_path = parts[0].split('https://huggingface.co/')[-1]
-            return 'huggingface', repo_path
-    return 'direct', uri
-
-def calculate_sha256(file_path):
-    sha256_hash = hashlib.sha256()
-    with open(file_path, 'rb') as f:
-        for byte_block in iter(lambda: f.read(4096), b''):
-            sha256_hash.update(byte_block)
-    return sha256_hash.hexdigest()
-
-def manual_safety_check_hf(repo_id):
-    scanResponse = requests.get('https://huggingface.co/api/models/' + repo_id + "/scan")
-    scan = scanResponse.json()
-    if scan['hasUnsafeFile']:
-        return scan
-    return None
-
-download_type, repo_id_or_url = parse_uri(uri)
-
-new_checksum =  None
-
-# Decide download method based on URI type
-if download_type == 'huggingface':
-    # Check if the repo is flagged as dangerous by HF
-    hazard = manual_safety_check_hf(repo_id_or_url)
-    if hazard != None:
-        print(f'Error: HuggingFace has detected security problems for {repo_id_or_url}: {str(hazard)}', filename=file_name)
-        sys.exit(5)
-    # Use HF API to pull sha
-    for file in get_paths_info(repo_id_or_url, [file_name], repo_type='model'):
-        try:
-            new_checksum = file.lfs.sha256
-            break
-        except Exception as e:
-            print(f'Error from Hugging Face Hub: {str(e)}', file=sys.stderr)
-            sys.exit(2)
-    if new_checksum is None:
-        try:
-            file_path = hf_hub_download(repo_id=repo_id_or_url, filename=file_name)
-        except Exception as e:
-            print(f'Error from Hugging Face Hub: {str(e)}', file=sys.stderr)
-            sys.exit(2)
-else:
-    response = requests.get(repo_id_or_url)
-    if response.status_code == 200:
-        with open(file_name, 'wb') as f:
-            f.write(response.content)
-        file_path = file_name
-    elif response.status_code == 404:
-        print(f'File not found: {response.status_code}', file=sys.stderr)
-        sys.exit(2)
-    else:
-        print(f'Error downloading file: {response.status_code}', file=sys.stderr)
-        sys.exit(1)
-
-if new_checksum is None:
-    new_checksum = calculate_sha256(file_path)
-    print(new_checksum)
-    os.remove(file_path)
-else:
-    print(new_checksum)
--- a/.github/checksum_checker.sh
+++ b/.github/checksum_checker.sh
@@ -14,14 +14,77 @@ function check_and_update_checksum() {
    idx="$5"

    # Download the file and calculate new checksum using Python
-    new_checksum=$(python3 ./check_and_update.py $uri)
-    result=$?
+    new_checksum=$(python3 -c "
+import hashlib
+from huggingface_hub import hf_hub_download, get_paths_info
+import requests
+import sys
+import os

-    if [[ result -eq 5]]; then
-        echo "Contaminated entry detected, deleting entry for $model_name..."
-        yq eval -i "del([$idx])" "$input_yaml"
-        return
-    fi
+uri = '$uri'
+file_name = uri.split('/')[-1]
+
+# Function to parse the URI and determine download method
+# Function to parse the URI and determine download method
+def parse_uri(uri):
+    if uri.startswith('huggingface://'):
+        repo_id = uri.split('://')[1]
+        return 'huggingface', repo_id.rsplit('/', 1)[0]
+    elif 'huggingface.co' in uri:
+        parts = uri.split('/resolve/')
+        if len(parts) > 1:
+            repo_path = parts[0].split('https://huggingface.co/')[-1]
+            return 'huggingface', repo_path
+    return 'direct', uri
+
+def calculate_sha256(file_path):
+    sha256_hash = hashlib.sha256()
+    with open(file_path, 'rb') as f:
+        for byte_block in iter(lambda: f.read(4096), b''):
+            sha256_hash.update(byte_block)
+    return sha256_hash.hexdigest()
+
+download_type, repo_id_or_url = parse_uri(uri)
+
+new_checksum =  None
+
+# Decide download method based on URI type
+if download_type == 'huggingface':
+    # Use HF API to pull sha
+    for file in get_paths_info(repo_id_or_url, [file_name], repo_type='model'):
+        try:
+            new_checksum = file.lfs.sha256
+            break
+        except Exception as e:
+            print(f'Error from Hugging Face Hub: {str(e)}', file=sys.stderr)
+            sys.exit(2)
+    if new_checksum is None:
+        try:
+            file_path = hf_hub_download(repo_id=repo_id_or_url, filename=file_name)
+        except Exception as e:
+            print(f'Error from Hugging Face Hub: {str(e)}', file=sys.stderr)
+            sys.exit(2)
+else:
+    response = requests.get(repo_id_or_url)
+    if response.status_code == 200:
+        with open(file_name, 'wb') as f:
+            f.write(response.content)
+        file_path = file_name
+    elif response.status_code == 404:
+        print(f'File not found: {response.status_code}', file=sys.stderr)
+        sys.exit(2)
+    else:
+        print(f'Error downloading file: {response.status_code}', file=sys.stderr)
+        sys.exit(1)
+
+if new_checksum is None:
+    new_checksum = calculate_sha256(file_path)
+    print(new_checksum)
+    os.remove(file_path)
+else:
+    print(new_checksum)
+
+")

    if [[ "$new_checksum" == "" ]]; then
        echo "Error calculating checksum for $file_name. Skipping..."
@@ -31,7 +94,7 @@ function check_and_update_checksum() {
    echo "Checksum for $file_name: $new_checksum"

    # Compare and update the YAML file if checksums do not match
-    
+    result=$?
    if [[ $result -eq 2 ]]; then
        echo "File not found, deleting entry for $file_name..."
        # yq eval -i "del(.[$idx].files[] | select(.filename == \"$file_name\"))" "$input_yaml"
--- a/.github/ci/modelslist.go
+++ b/.github/ci/modelslist.go
@@ -75,7 +75,7 @@ var modelPageTemplate string = `
    <div class="container mx-auto px-4 py-4">
        <div class="flex items-center justify-between">
            <div class="flex items-center">
-                <a href="/" class="text-white text-xl font-bold"><img src="https://github.com/mudler/LocalAI/assets/2420543/0966aa2a-166e-4f99-a3e5-6c915fc997dd" alt="LocalAI Logo" class="h-10 mr-3 border-2 border-gray-300 shadow rounded"></a>
+                <a href="/" class="text-white text-xl font-bold"><img src="https://github.com/go-skynet/LocalAI/assets/2420543/0966aa2a-166e-4f99-a3e5-6c915fc997dd" alt="LocalAI Logo" class="h-10 mr-3 border-2 border-gray-300 shadow rounded"></a>
                <a href="/" class="text-white text-xl font-bold">LocalAI</a>
            </div>
            <!-- Menu button for small screens -->
@@ -92,9 +92,9 @@ var modelPageTemplate string = `
        <!-- Collapsible menu for small screens -->
        <div class="hidden lg:hidden" id="mobile-menu">
            <div class="pt-4 pb-3 border-t border-gray-700">
-
+                
                <a href="https://localai.io" class="block text-gray-400 hover:text-white px-3 py-2 rounded mt-1" target="_blank" ><i class="fas fa-book-reader pr-2"></i> Documentation</a>
-
+               
            </div>
        </div>
    </div>
@@ -114,17 +114,17 @@ var modelPageTemplate string = `

 	<h2 class="text-center text-3xl font-semibold text-gray-100">

-	 🖼️ Available {{.AvailableModels}} models</i> <a href="https://localai.io/models/" target="_blank" >
+	 🖼️ Available {{.AvailableModels}} models</i> repositories     <a href="https://localai.io/models/" target="_blank" >
 			<i class="fas fa-circle-info pr-2"></i>
-		</a></h2>
+		</a></h2> 

-	<h3>
-	Refer to the Model gallery <a href="https://localai.io/models/" target="_blank" ><i class="fas fa-circle-info pr-2"></i></a> for more information on how to use the models with LocalAI.<br>
+	<h3>	  
+	Refer to <a href="https://localai.io/models" target=_blank> Model gallery</a> for more information on how to use the models with LocalAI.

 	You can install models with the CLI command <code>local-ai models install <model-name></code>. or by using the WebUI.
 	</h3>
-
-	<input class="form-control appearance-none block w-full mt-5 px-3 py-2 text-base font-normal text-gray-300 pb-2 mb-5 bg-gray-800 bg-clip-padding border border-solid border-gray-600 rounded transition ease-in-out m-0 focus:text-gray-300 focus:bg-gray-900 focus:border-blue-500 focus:outline-none" type="search"
+  
+	<input class="form-control appearance-none block w-full mt-5 px-3 py-2 text-base font-normal text-gray-300 pb-2 mb-5 bg-gray-800 bg-clip-padding border border-solid border-gray-600 rounded transition ease-in-out m-0 focus:text-gray-300 focus:bg-gray-900 focus:border-blue-500 focus:outline-none" type="search" 
 	id="searchbox" placeholder="Live search keyword..">
 	  <div class="dark grid grid-cols-1 grid-rows-1 md:grid-cols-3 block rounded-lg shadow-secondary-1 dark:bg-surface-dark">
 		{{ range $_, $model := .Models }}
@@ -139,10 +139,10 @@ var modelPageTemplate string = `
 			</div>
 	  		<div class="p-6 text-surface dark:text-white">
 				<h5 class="mb-2 text-xl font-medium leading-tight">{{$model.Name}}</h5>
-
-
+				
+				   
 				<p class="mb-4 text-base truncate">{{ $model.Description }}</p>
-
+		
 			</div>
 			<div class="px-6 pt-4 pb-2">

@@ -178,7 +178,7 @@ var modelPageTemplate string = `
                    {{ $model.Description }}

                    </p>
-
+                    
                    <p class="text-base leading-relaxed text-gray-500 dark:text-gray-400">
                    To install the model with the CLI, run: <br>
                    <code> local-ai models install {{$model.Name}} </code> <br>
@@ -193,7 +193,7 @@ var modelPageTemplate string = `
                    <ul>
                    {{ range $_, $u := $model.URLs }}
                    <li><a href="{{ $u }}" target=_blank><i class="fa-solid fa-link"></i> {{ $u }}</a></li>
-                    {{ end }}
+                    {{ end }}  
                    </ul>
                    </p>
                </div>
@@ -209,7 +209,7 @@ var modelPageTemplate string = `
 			</div>
 		</div>
 		</div>
-		{{ end }}
+		{{ end }}      

 		</div>
  </div>
@@ -221,10 +221,10 @@ var lazyLoadInstance = new LazyLoad({
 });

 let cards = document.querySelectorAll('.box')
-
+    
 function liveSearch() {
    let search_query = document.getElementById("searchbox").value;
-
+    
    //Use innerText if all contents are visible
    //Use textContent for including hidden elements
    for (var i = 0; i < cards.length; i++) {
@@ -238,8 +238,8 @@ function liveSearch() {
 }

 //A little delay
-let typingTimer;
-let typeInterval = 500;
+let typingTimer;               
+let typeInterval = 500;  
 let searchInput = document.getElementById('searchbox');

 searchInput.addEventListener('keyup', () => {
--- a/.github/release.yml
+++ b/.github/release.yml
@@ -13,9 +13,6 @@ changelog:
      labels:
        - bug
        - regression
-    - title: "🖧 P2P area"
-      labels:
-         - area/p2p
    - title: Exciting New Features 🎉
      labels:
        - Semver-Minor
--- a/.github/workflows/image-pr.yml
+++ b/.github/workflows/image-pr.yml
@@ -32,7 +32,7 @@ jobs:
    strategy:
      # Pushing with all jobs in parallel
      # eats the bandwidth of all the nodes
-      max-parallel: ${{ github.event_name != 'pull_request' && 4 || 8 }}
+      max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
      matrix:
        include:
          - build-type: ''
@@ -46,7 +46,7 @@ jobs:
            makeflags: "--jobs=3 --output-sync=target"
          - build-type: 'cublas'
            cuda-major-version: "12"
-            cuda-minor-version: "4"
+            cuda-minor-version: "1"
            platforms: 'linux/amd64'
            tag-latest: 'false'
            tag-suffix: '-cublas-cuda12-ffmpeg'
@@ -119,7 +119,7 @@ jobs:
            makeflags: "--jobs=3 --output-sync=target"
          - build-type: 'cublas'
            cuda-major-version: "12"
-            cuda-minor-version: "4"
+            cuda-minor-version: "1"
            platforms: 'linux/amd64'
            tag-latest: 'false'
            tag-suffix: '-cublas-cuda12-ffmpeg-core'
@@ -127,13 +127,4 @@ jobs:
            image-type: 'core'
            runs-on: 'ubuntu-latest'
            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=4 --output-sync=target"
-          - build-type: 'vulkan'
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-vulkan-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=4 --output-sync=target"
+            makeflags: "--jobs=4 --output-sync=target"
--- a/.github/workflows/image.yml
+++ b/.github/workflows/image.yml
@@ -39,7 +39,7 @@ jobs:
    strategy:
      # Pushing with all jobs in parallel
      # eats the bandwidth of all the nodes
-      max-parallel: ${{ github.event_name != 'pull_request' && 6 || 10 }}
+      max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
      matrix:
        include:
          # Extra images
@@ -75,7 +75,7 @@ jobs:
            makeflags: "--jobs=3 --output-sync=target"
          - build-type: 'cublas'
            cuda-major-version: "12"
-            cuda-minor-version: "4"
+            cuda-minor-version: "1"
            platforms: 'linux/amd64'
            tag-latest: 'false'
            tag-suffix: '-cublas-cuda12'
@@ -100,7 +100,7 @@ jobs:
            makeflags: "--jobs=3 --output-sync=target"
          - build-type: 'cublas'
            cuda-major-version: "12"
-            cuda-minor-version: "4"
+            cuda-minor-version: "1"
            platforms: 'linux/amd64'
            tag-latest: 'auto'
            tag-suffix: '-cublas-cuda12-ffmpeg'
@@ -232,7 +232,7 @@ jobs:
            grpc-base-image: "ubuntu:22.04"
            runs-on: 'arc-runner-set'
            makeflags: "--jobs=3 --output-sync=target"
-
+  
  core-image-build:
    uses: ./.github/workflows/image_build.yml
    with:
@@ -257,7 +257,6 @@ jobs:
      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
    strategy:
-      max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
      matrix:
        include:
          - build-type: ''
@@ -267,7 +266,7 @@ jobs:
            ffmpeg: 'true'
            image-type: 'core'
            base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
            aio: "-aio-cpu"
            latest-image: 'latest-cpu'
            latest-image-aio: 'latest-aio-cpu'
@@ -281,18 +280,18 @@ jobs:
            ffmpeg: ''
            image-type: 'core'
            base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
            makeflags: "--jobs=4 --output-sync=target"
          - build-type: 'cublas'
            cuda-major-version: "12"
-            cuda-minor-version: "4"
+            cuda-minor-version: "1"
            platforms: 'linux/amd64'
            tag-latest: 'false'
            tag-suffix: '-cublas-cuda12-core'
            ffmpeg: ''
            image-type: 'core'
            base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
            makeflags: "--jobs=4 --output-sync=target"
          - build-type: 'cublas'
            cuda-major-version: "11"
@@ -302,27 +301,17 @@ jobs:
            tag-suffix: '-cublas-cuda11-ffmpeg-core'
            ffmpeg: 'true'
            image-type: 'core'
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
            base-image: "ubuntu:22.04"
            makeflags: "--jobs=4 --output-sync=target"
          - build-type: 'cublas'
            cuda-major-version: "12"
-            cuda-minor-version: "4"
+            cuda-minor-version: "1"
            platforms: 'linux/amd64'
            tag-latest: 'false'
            tag-suffix: '-cublas-cuda12-ffmpeg-core'
            ffmpeg: 'true'
            image-type: 'core'
-            runs-on: 'arc-runner-set'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=4 --output-sync=target"
-          - build-type: 'vulkan'
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-vulkan-ffmpeg-core'
-            latest-image: 'latest-vulkan-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
            base-image: "ubuntu:22.04"
            makeflags: "--jobs=4 --output-sync=target"
--- a/.github/workflows/image_build.yml
+++ b/.github/workflows/image_build.yml
@@ -19,11 +19,11 @@ on:
        type: string
      cuda-major-version:
        description: 'CUDA major version'
-        default: "12"
+        default: "11"
        type: string
      cuda-minor-version:
        description: 'CUDA minor version'
-        default: "4"
+        default: "7"
        type: string
      platforms:
        description: 'Platforms'
@@ -324,7 +324,7 @@ jobs:
          docker pull quay.io/go-skynet/local-ai:${{ steps.meta_aio.outputs.version }}
          docker tag quay.io/go-skynet/local-ai:${{ steps.meta_aio.outputs.version }} quay.io/go-skynet/local-ai:${{ inputs.latest-image-aio }}
          docker push quay.io/go-skynet/local-ai:${{ inputs.latest-image-aio }}
-
+  
      - name: job summary
        run: |
          echo "Built image: ${{ steps.meta.outputs.labels }}" >> $GITHUB_STEP_SUMMARY
--- a/.github/workflows/notify-models.yaml
+++ b/.github/workflows/notify-models.yaml
@@ -1,170 +0,0 @@
-name: Notifications for new models
-on:
-  pull_request:
-     types:
-       - closed
-
-jobs:
-  notify-discord:
-    if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model')) }}
-    env:
-        MODEL_NAME: hermes-2-theta-llama-3-8b
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v4
-      with:
-        fetch-depth: 0 # needed to checkout all branches for this Action to work
-    - name: Start LocalAI
-      run: |
-        echo "Starting LocalAI..."
-        docker run -e -ti -d --name local-ai -p 8080:8080 localai/localai:master-ffmpeg-core run --debug $MODEL_NAME
-        until [ "`docker inspect -f {{.State.Health.Status}} local-ai`" == "healthy" ]; do echo "Waiting for container to be ready";  docker logs --tail 10 local-ai; sleep 2; done
-      # Check the PR diff using the current branch and the base branch of the PR
-    - uses: GrantBirki/git-diff-action@v2.7.0
-      id: git-diff-action
-      with:
-            json_diff_file_output: diff.json
-            raw_diff_file_output: diff.txt
-            file_output_only: "true"
-    - name: Summarize
-      env:
-        DIFF: ${{ steps.git-diff-action.outputs.raw-diff-path }}
-      id: summarize
-      run: |
-            input="$(cat $DIFF)"
-
-            # Define the LocalAI API endpoint
-            API_URL="http://localhost:8080/chat/completions"
-
-            # Create a JSON payload using jq to handle special characters
-            json_payload=$(jq -n --arg input "$input" '{
-            model: "'$MODEL_NAME'",
-            messages: [
-                {
-                role: "system",
-                content: "You are LocalAI-bot. Write a discord message to notify everyone about the new model from the git diff. Make it informal. An example can include: the URL of the model, the name, and a brief description of the model if exists. Also add an hint on how to install it in LocalAI and that can be browsed over https://models.localai.io. For example: local-ai run model_name_here"
-                },
-                {
-                role: "user",
-                content: $input
-                }
-            ]
-            }')
-
-            # Send the request to LocalAI
-            response=$(curl -s -X POST $API_URL \
-            -H "Content-Type: application/json" \
-            -d "$json_payload")
-
-            # Extract the summary from the response
-            summary="$(echo $response | jq -r '.choices[0].message.content')"
-
-            # Print the summary
-            #  -H "Authorization: Bearer $API_KEY" \
-            echo "Summary:"
-            echo "$summary"
-            echo "payload sent"
-            echo "$json_payload"
-            {
-                echo 'message<<EOF'
-                echo "$summary"
-                echo EOF
-              } >> "$GITHUB_OUTPUT"
-            docker logs --tail 10 local-ai
-    - name: Discord notification
-      env:
-        DISCORD_WEBHOOK: ${{ secrets.DISCORD_WEBHOOK_URL }}
-        DISCORD_USERNAME: "LocalAI-Bot"
-        DISCORD_AVATAR: "https://avatars.githubusercontent.com/u/139863280?v=4"
-      uses: Ilshidur/action-discord@master
-      with:
-        args: ${{ steps.summarize.outputs.message }}
-    - name: Setup tmate session if fails
-      if: ${{ failure() }}
-      uses: mxschmitt/action-tmate@v3.18
-      with:
-        detached: true
-        connect-timeout-seconds: 180
-        limit-access-to-actor: true
-  notify-twitter:
-    if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model')) }}
-    env:
-        MODEL_NAME: hermes-2-theta-llama-3-8b
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v4
-      with:
-        fetch-depth: 0 # needed to checkout all branches for this Action to work
-    - name: Start LocalAI
-      run: |
-        echo "Starting LocalAI..."
-        docker run -e -ti -d --name local-ai -p 8080:8080 localai/localai:master-ffmpeg-core run --debug $MODEL_NAME
-        until [ "`docker inspect -f {{.State.Health.Status}} local-ai`" == "healthy" ]; do echo "Waiting for container to be ready";  docker logs --tail 10 local-ai; sleep 2; done
-      # Check the PR diff using the current branch and the base branch of the PR
-    - uses: GrantBirki/git-diff-action@v2.7.0
-      id: git-diff-action
-      with:
-            json_diff_file_output: diff.json
-            raw_diff_file_output: diff.txt
-            file_output_only: "true"
-    - name: Summarize
-      env:
-        DIFF: ${{ steps.git-diff-action.outputs.raw-diff-path }}
-      id: summarize
-      run: |
-            input="$(cat $DIFF)"
-
-            # Define the LocalAI API endpoint
-            API_URL="http://localhost:8080/chat/completions"
-
-            # Create a JSON payload using jq to handle special characters
-            json_payload=$(jq -n --arg input "$input" '{
-            model: "'$MODEL_NAME'",
-            messages: [
-                {
-                role: "system",
-                content: "You are LocalAI-bot. Write a twitter message to notify everyone about the new model from the git diff. Make it informal and really short. An example can include: the name, and a brief description of the model if exists. Also add an hint on how to install it in LocalAI. For example: local-ai run model_name_here"
-                },
-                {
-                role: "user",
-                content: $input
-                }
-            ]
-            }')
-
-            # Send the request to LocalAI
-            response=$(curl -s -X POST $API_URL \
-            -H "Content-Type: application/json" \
-            -d "$json_payload")
-
-            # Extract the summary from the response
-            summary="$(echo $response | jq -r '.choices[0].message.content')"
-
-            # Print the summary
-            #  -H "Authorization: Bearer $API_KEY" \
-            echo "Summary:"
-            echo "$summary"
-            echo "payload sent"
-            echo "$json_payload"
-            {
-                echo 'message<<EOF'
-                echo "$summary"
-                echo EOF
-              } >> "$GITHUB_OUTPUT"
-            docker logs --tail 10 local-ai
-    - uses: Eomm/why-don-t-you-tweet@v2
-      with:
-        tweet-message: ${{ steps.summarize.outputs.message }}
-      env:
-        # Get your tokens from https://developer.twitter.com/apps
-        TWITTER_CONSUMER_API_KEY: ${{ secrets.TWITTER_APP_KEY }}
-        TWITTER_CONSUMER_API_SECRET: ${{ secrets.TWITTER_APP_SECRET }}
-        TWITTER_ACCESS_TOKEN: ${{ secrets.TWITTER_ACCESS_TOKEN }}
-        TWITTER_ACCESS_TOKEN_SECRET: ${{ secrets.TWITTER_ACCESS_TOKEN_SECRET }}
-    - name: Setup tmate session if fails
-      if: ${{ failure() }}
-      uses: mxschmitt/action-tmate@v3.18
-      with:
-        detached: true
-        connect-timeout-seconds: 180
-        limit-access-to-actor: true
--- a/.github/workflows/notify-releases.yaml
+++ b/.github/workflows/notify-releases.yaml
@@ -1,65 +0,0 @@
-name: Release notifications
-on:
-  release:
-    types:
-      - published
-
-jobs:
-  notify-discord:
-    runs-on: ubuntu-latest
-    env:
-        RELEASE_BODY: ${{ github.event.release.body }}
-        RELEASE_TITLE: ${{ github.event.release.name }}
-        RELEASE_TAG_NAME: ${{ github.event.release.tag_name }}
-    steps:
-    - name: Start LocalAI
-      run: |
-        echo "Starting LocalAI..."
-        docker run -e -ti -d --name local-ai -p 8080:8080 localai/localai:master-ffmpeg-core run --debug $MODEL_NAME
-        until [ "`docker inspect -f {{.State.Health.Status}} local-ai`" == "healthy" ]; do echo "Waiting for container to be ready";  docker logs --tail 10 local-ai; sleep 2; done
-    - name: Summarize
-      id: summarize
-      run: |
-            input="$RELEASE_TITLE\b$RELEASE_BODY"
-
-            # Define the LocalAI API endpoint
-            API_URL="http://localhost:8080/chat/completions"
-
-            # Create a JSON payload using jq to handle special characters
-            json_payload=$(jq -n --arg input "$input" '{
-            model: "'$MODEL_NAME'",
-            messages: [
-                {
-                role: "system",
-                content: "Write a discord message with a bullet point summary of the release notes."
-                },
-                {
-                role: "user",
-                content: $input
-                }
-            ]
-            }')
-
-            # Send the request to LocalAI API
-            response=$(curl -s -X POST $API_URL \
-            -H "Content-Type: application/json" \
-            -d "$json_payload")
-
-            # Extract the summary from the response
-            summary=$(echo $response | jq -r '.choices[0].message.content')
-
-            # Print the summary
-            #  -H "Authorization: Bearer $API_KEY" \
-            {
-                echo 'message<<EOF'
-                echo "$summary"
-                echo EOF
-              } >> "$GITHUB_OUTPUT"
-    - name: Discord notification
-      env:
-        DISCORD_WEBHOOK: ${{ secrets.DISCORD_WEBHOOK_URL_RELEASE }}
-        DISCORD_USERNAME: "LocalAI-Bot"
-        DISCORD_AVATAR: "https://avatars.githubusercontent.com/u/139863280?v=4"
-      uses: Ilshidur/action-discord@master
-      with:
-        args: ${{ steps.summarize.outputs.message }}
--- a/.github/workflows/release.yaml
+++ b/.github/workflows/release.yaml
@@ -31,8 +31,8 @@ jobs:
      - name: Dependencies
        run: |
          sudo apt-get update
-          sudo apt-get install build-essential ffmpeg protobuf-compiler ccache gawk
-          sudo apt-get install -qy binutils-aarch64-linux-gnu gcc-aarch64-linux-gnu g++-aarch64-linux-gnu libgmock-dev
+          sudo apt-get install build-essential ffmpeg protobuf-compiler ccache
+          sudo apt-get install -qy binutils-aarch64-linux-gnu gcc-aarch64-linux-gnu g++-aarch64-linux-gnu
      - name: Install CUDA Dependencies
        run: |
          curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/cross-linux-aarch64/cuda-keyring_1.1-1_all.deb
@@ -51,21 +51,7 @@ jobs:
        if: steps.cache-grpc.outputs.cache-hit != 'true'
        run: |

-          git clone --recurse-submodules -b ${{ env.GRPC_VERSION }} --depth 1 --shallow-submodules https://github.com/grpc/grpc
-          GRPC_DIR=$PWD/grpc/
-          echo "include(FetchContent)" >> $GRPC_DIR/CMakeLists.txt
-          echo "FetchContent_Declare(" >> $GRPC_DIR/CMakeLists.txt
-          echo "  googletest" >> $GRPC_DIR/CMakeLists.txt
-          echo "  URL https://github.com/google/googletest/archive/03597a01ee50ed33e9dfd640b249b4be3799d395.zip" >> $GRPC_DIR/CMakeLists.txt
-          echo ")" >> $GRPC_DIR/CMakeLists.txt
-          echo "FetchContent_MakeAvailable(googletest)" >> $GRPC_DIR/CMakeLists.txt
-          GRPC_DIR=$PWD/grpc/third_party/abseil-cpp
-          echo "include(FetchContent)" >> $GRPC_DIR/CMakeLists.txt
-          echo "FetchContent_Declare(" >> $GRPC_DIR/CMakeLists.txt
-          echo "  googletest" >> $GRPC_DIR/CMakeLists.txt
-          echo "  URL https://github.com/google/googletest/archive/03597a01ee50ed33e9dfd640b249b4be3799d395.zip" >> $GRPC_DIR/CMakeLists.txt
-          echo ")" >> $GRPC_DIR/CMakeLists.txt
-          echo "FetchContent_MakeAvailable(googletest)" >> $GRPC_DIR/CMakeLists.txt
+          git clone --recurse-submodules -b ${{ env.GRPC_VERSION }} --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
          cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
            -DgRPC_BUILD_TESTS=OFF \
            ../.. && sudo make --jobs 5 --output-sync=target
@@ -114,13 +100,7 @@ jobs:
          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.0
          export PATH=$PATH:$GOPATH/bin
          export PATH=/usr/local/cuda/bin:$PATH
-          sudo rm -rf /usr/aarch64-linux-gnu/lib/libstdc++.so.6
-          sudo cp -rf /usr/aarch64-linux-gnu/lib/libstdc++.so* /usr/aarch64-linux-gnu/lib/libstdc++.so.6
-          sudo cp /usr/aarch64-linux-gnu/lib/ld-linux-aarch64.so.1 ld.so
-          BACKEND_LIBS="./grpc/cmake/cross_build/third_party/re2/libre2.a ./grpc/cmake/cross_build/libgrpc.a ./grpc/cmake/cross_build/libgrpc++.a ./grpc/cmake/cross_build/third_party/protobuf/libprotobuf.a /usr/aarch64-linux-gnu/lib/libc.so.6 /usr/aarch64-linux-gnu/lib/libstdc++.so.6 /usr/aarch64-linux-gnu/lib/libgomp.so.1 /usr/aarch64-linux-gnu/lib/libm.so.6 /usr/aarch64-linux-gnu/lib/libgcc_s.so.1 /usr/aarch64-linux-gnu/lib/libdl.so.2 /usr/aarch64-linux-gnu/lib/libpthread.so.0 ./ld.so" \
-          GOOS=linux \
-          GOARCH=arm64 \
-          CMAKE_ARGS="-DProtobuf_INCLUDE_DIRS=$CROSS_STAGING_PREFIX/include -DProtobuf_DIR=$CROSS_STAGING_PREFIX/lib/cmake/protobuf -DgRPC_DIR=$CROSS_STAGING_PREFIX/lib/cmake/grpc -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++" make dist-cross-linux-arm64
+          GO_TAGS=p2p GOOS=linux GOARCH=arm64 CMAKE_ARGS="-DProtobuf_INCLUDE_DIRS=$CROSS_STAGING_PREFIX/include -DProtobuf_DIR=$CROSS_STAGING_PREFIX/lib/cmake/protobuf -DgRPC_DIR=$CROSS_STAGING_PREFIX/lib/cmake/grpc -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++" make dist-cross-linux-arm64
      - uses: actions/upload-artifact@v4
        with:
          name: LocalAI-linux-arm64
@@ -131,13 +111,7 @@ jobs:
        with:
          files: |
            release/*
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
+
  build-linux:
    runs-on: arc-runner-set
    steps:
@@ -160,7 +134,7 @@ jobs:
      - name: Dependencies
        run: |
          sudo apt-get update
-          sudo apt-get install -y wget curl build-essential ffmpeg protobuf-compiler ccache gawk cmake libgmock-dev
+          sudo apt-get install -y wget curl build-essential ffmpeg protobuf-compiler ccache cmake
      - name: Intel Dependencies
        run: |
          wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | sudo tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null
@@ -180,15 +154,15 @@ jobs:
          ROCM_VERSION: "6.1"
          AMDGPU_VERSION: "6.1"
        run: |
-            set -ex
+            set -ex 

            sudo apt-get update
-            sudo DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends ca-certificates curl libnuma-dev gnupg
-
-            curl -sL https://repo.radeon.com/rocm/rocm.gpg.key | sudo apt-key add -
-
+            sudo DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends ca-certificates curl libnuma-dev gnupg 
+            
+            curl -sL https://repo.radeon.com/rocm/rocm.gpg.key | sudo apt-key add - 
+              
            printf "deb [arch=amd64] https://repo.radeon.com/rocm/apt/$ROCM_VERSION/ jammy main" | sudo tee /etc/apt/sources.list.d/rocm.list
-
+            
            printf "deb [arch=amd64] https://repo.radeon.com/amdgpu/$AMDGPU_VERSION/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
            printf 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
            sudo apt-get update
@@ -196,10 +170,10 @@ jobs:
            sudo DEBIAN_FRONTEND=noninteractive apt-get install -y \
                hipblas-dev rocm-dev \
                rocblas-dev
-
+          
            sudo apt-get clean
            sudo rm -rf /var/lib/apt/lists/*
-            sudo ldconfig
+            sudo ldconfig 
      - name: Cache grpc
        id: cache-grpc
        uses: actions/cache@v4
@@ -216,7 +190,6 @@ jobs:
      - name: Install gRPC
        run: |
          cd grpc && cd cmake/build && sudo make --jobs 5 --output-sync=target install
-      # BACKEND_LIBS needed for gpu-workload: /opt/intel/oneapi/*/lib/libiomp5.so /opt/intel/oneapi/*/lib/libmkl_core.so /opt/intel/oneapi/*/lib/libmkl_core.so.2 /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so.2 /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so.4 /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so.2 /opt/intel/oneapi/*/lib/libsycl.so /opt/intel/oneapi/*/lib/libsycl.so.7 /opt/intel/oneapi/*/lib/libsycl.so.7.1.0 /opt/rocm-*/lib/libamdhip64.so /opt/rocm-*/lib/libamdhip64.so.5 /opt/rocm-*/lib/libamdhip64.so.6 /opt/rocm-*/lib/libamdhip64.so.6.1.60100 /opt/rocm-*/lib/libhipblas.so /opt/rocm-*/lib/libhipblas.so.2 /opt/rocm-*/lib/libhipblas.so.2.1.60100 /opt/rocm-*/lib/librocblas.so /opt/rocm-*/lib/librocblas.so.4 /opt/rocm-*/lib/librocblas.so.4.1.60100 /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1.0.0 /usr/lib/x86_64-linux-gnu/libm.so.6 /usr/lib/x86_64-linux-gnu/libgcc_s.so.1 /usr/lib/x86_64-linux-gnu/libc.so.6 /usr/lib/x86_64-linux-gnu/librt.so.1 /usr/local/cuda-*/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-*/targets/x86_64-linux/lib/stubs/libcuda.so
      - name: Build
        id: build
        run: |
@@ -226,10 +199,7 @@ jobs:
          export PATH=/usr/local/cuda/bin:$PATH
          export PATH=/opt/rocm/bin:$PATH
          source /opt/intel/oneapi/setvars.sh
-          GRPC_DIR=$PWD/backend/cpp/llama
-          sudo cp /lib64/ld-linux-x86-64.so.2 ld.so
-          BACKEND_LIBS="./ld.so ./sources/go-piper/piper/build/fi/lib/libfmt.a ./sources/go-piper/piper-phonemize/pi/lib/libonnxruntime.so.1.14.1 ./sources/go-piper/piper-phonemize/pi/src/libespeak-ng/libespeak-ng.so /usr/lib/x86_64-linux-gnu/libdl.so.2 /usr/lib/x86_64-linux-gnu/librt.so.1 /usr/lib/x86_64-linux-gnu/libpthread.so.0 ./sources/go-piper/piper-phonemize/pi/lib/libpiper_phonemize.so.1 ./sources/go-piper/piper/build/si/lib/libspdlog.a ./sources/go-piper/espeak/ei/lib/libucd.so" \
-          make -j4 dist
+          GO_TAGS=p2p make -j4 dist
      - uses: actions/upload-artifact@v4
        with:
          name: LocalAI-linux
@@ -240,13 +210,7 @@ jobs:
        with:
          files: |
            release/*
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
+
  build-stablediffusion:
    runs-on: ubuntu-latest
    steps:
@@ -282,48 +246,6 @@ jobs:
          files: |
            release/*

-  build-macOS-x86_64:
-    runs-on: macos-13
-    steps:
-      - name: Clone
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-      - uses: actions/setup-go@v5
-        with:
-          go-version: '1.21.x'
-          cache: false
-      - name: Dependencies
-        run: |
-          brew install protobuf grpc
-          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@8ba23be9613c672d40ae261d2a1335d639bdd59b
-          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.0
-      - name: Build
-        id: build
-        run: |
-          export C_INCLUDE_PATH=/usr/local/include
-          export CPLUS_INCLUDE_PATH=/usr/local/include
-          export PATH=$PATH:$GOPATH/bin
-
-          make dist
-      - uses: actions/upload-artifact@v4
-        with:
-          name: LocalAI-MacOS-x86_64
-          path: release/
-      - name: Release
-        uses: softprops/action-gh-release@v2
-        if: startsWith(github.ref, 'refs/tags/')
-        with:
-          files: |
-            release/*
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
-
  build-macOS-arm64:
    runs-on: macos-14
    steps:
@@ -335,6 +257,10 @@ jobs:
        with:
          go-version: '1.21.x'
          cache: false
+      - name: Setup tmate session if tests fail
+        uses: mxschmitt/action-tmate@v3.18
+        with:
+          limit-access-to-actor: true
      - name: Dependencies
        run: |
          brew install protobuf grpc
@@ -346,8 +272,7 @@ jobs:
          export C_INCLUDE_PATH=/usr/local/include
          export CPLUS_INCLUDE_PATH=/usr/local/include
          export PATH=$PATH:$GOPATH/bin
-
-          make dist
+          GO_TAGS=p2p make dist
      - uses: actions/upload-artifact@v4
        with:
          name: LocalAI-MacOS-arm64
@@ -358,10 +283,3 @@ jobs:
        with:
          files: |
            release/*
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -71,7 +71,6 @@ jobs:
        run: |
          sudo apt-get update
          sudo apt-get install build-essential curl ffmpeg
-          sudo apt-get install -y libgmock-dev
          curl https://repo.anaconda.com/pkgs/misc/gpgkeys/anaconda.asc | gpg --dearmor > conda.gpg && \
             sudo install -o root -g root -m 644 conda.gpg /usr/share/keyrings/conda-archive-keyring.gpg && \
             gpg --keyring /usr/share/keyrings/conda-archive-keyring.gpg --no-default-keyring --fingerprint 34161F5BF5EB1D4BFBBB8F0A8AEB4F8B29D82806 && \
@@ -221,7 +220,7 @@ jobs:
          export CPLUS_INCLUDE_PATH=/usr/local/include
          # Used to run the newer GNUMake version from brew that supports --output-sync
          export PATH="/opt/homebrew/opt/make/libexec/gnubin:$PATH"
-          BUILD_TYPE="GITHUB_CI_HAS_BROKEN_METAL" CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF" make --jobs 4 --output-sync=target test
+          BUILD_TYPE="GITHUB_CI_HAS_BROKEN_METAL" CMAKE_ARGS="-DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF" make --jobs 4 --output-sync=target test
      - name: Setup tmate session if tests fail
        if: ${{ failure() }}
        uses: mxschmitt/action-tmate@v3.18
--- a/26
+++ b/26
@@ -33,7 +33,7 @@ RUN curl -L -s https://go.dev/dl/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz | ta
 ENV PATH $PATH:/root/go/bin:/usr/local/go/bin

 # Install grpc compilers
-RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2 && \
+RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.1 && \
    go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af

 COPY --chmod=644 custom-ca-certs/* /usr/local/share/ca-certificates/
@@ -98,27 +98,11 @@ RUN pip install --user grpcio-tools
 FROM requirements-${IMAGE_TYPE} AS requirements-drivers

 ARG BUILD_TYPE
-ARG CUDA_MAJOR_VERSION=12
-ARG CUDA_MINOR_VERSION=4
+ARG CUDA_MAJOR_VERSION=11
+ARG CUDA_MINOR_VERSION=8

 ENV BUILD_TYPE=${BUILD_TYPE}

-# Vulkan requirements
-RUN <<EOT bash
-    if [ "${BUILD_TYPE}" = "vulkan" ]; then
-        apt-get update && \
-        apt-get install -y  --no-install-recommends \
-                        software-properties-common pciutils wget gpg-agent && \
-        wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
-        wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
-        apt-get update && \
-            apt-get install -y \
-            vulkan-sdk && \
-        apt-get clean && \
-        rm -rf /var/lib/apt/lists/*
-    fi
-EOT
-
 # CuBLAS requirements
 RUN <<EOT bash
    if [ "${BUILD_TYPE}" = "cublas" ]; then
@@ -282,8 +266,6 @@ COPY --from=grpc /opt/grpc /usr/local

 # Rebuild with defaults backends
 WORKDIR /build
-
-## Build the binary
 RUN make build

 RUN if [ ! -d "/build/sources/go-piper/piper-phonemize/pi/lib/" ]; then \
@@ -310,7 +292,7 @@ ENV REBUILD=false
 ENV HEALTHCHECK_ENDPOINT=http://localhost:8080/readyz
 ENV MAKEFLAGS=${MAKEFLAGS}

-ARG CUDA_MAJOR_VERSION=12
+ARG CUDA_MAJOR_VERSION=11
 ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
 ENV NVIDIA_REQUIRE_CUDA="cuda>=${CUDA_MAJOR_VERSION}.0"
 ENV NVIDIA_VISIBLE_DEVICES=all
--- a/107
+++ b/107
@@ -3,11 +3,9 @@ GOTEST=$(GOCMD) test
 GOVET=$(GOCMD) vet
 BINARY_NAME=local-ai

-DETECT_LIBS?=true
-
 # llama.cpp versions
 GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=fd560fe680c72fd0a0af2bc8881add20ad919071
+CPPLLAMA_VERSION?=963552903f51043ee947a8deeaaa7ec00bc3f1a4

 # gpt4all version
 GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
@@ -18,7 +16,7 @@ RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp
 RWKV_VERSION?=661e7ae26d442f5cfebd2a0881b44e8c55949ec6

 # whisper.cpp version
-WHISPER_CPP_VERSION?=1c31f9d4a8936aec550e6c4dc9ca5cae3b4f304a
+WHISPER_CPP_VERSION?=420b6abc54008ab634f5887dc45bd77122c2f320

 # bert.cpp version
 BERT_VERSION?=710044b124545415f555e4260d16b146c725a6e4
@@ -35,11 +33,9 @@ TINYDREAM_VERSION?=c04fa463ace9d9a6464313aa5f9cd0f953b6c057
 export BUILD_TYPE?=
 export STABLE_BUILD_TYPE?=$(BUILD_TYPE)
 export CMAKE_ARGS?=
-export BACKEND_LIBS?=

 CGO_LDFLAGS?=
 CGO_LDFLAGS_WHISPER?=
-CGO_LDFLAGS_WHISPER+=-lggml
 CUDA_LIBPATH?=/usr/local/cuda/lib64/
 GO_TAGS?=
 BUILD_ID?=
@@ -53,12 +49,12 @@ RANDOM := $(shell bash -c 'echo $$RANDOM')
 VERSION?=$(shell git describe --always --tags || echo "dev" )
 # go tool nm ./local-ai | grep Commit
 LD_FLAGS?=
-override LD_FLAGS += -X "github.com/mudler/LocalAI/internal.Version=$(VERSION)"
-override LD_FLAGS += -X "github.com/mudler/LocalAI/internal.Commit=$(shell git rev-parse HEAD)"
+override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Version=$(VERSION)"
+override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Commit=$(shell git rev-parse HEAD)"

 OPTIONAL_TARGETS?=

-export OS := $(shell uname -s)
+OS := $(shell uname -s)
 ARCH := $(shell uname -m)
 GREEN  := $(shell tput -Txterm setaf 2)
 YELLOW := $(shell tput -Txterm setaf 3)
@@ -84,42 +80,29 @@ ifeq ($(OS),Darwin)
 		BUILD_TYPE=metal
 	# disable metal if on Darwin and any other value is explicitly passed.
 	else ifneq ($(BUILD_TYPE),metal)
-		CMAKE_ARGS+=-DGGML_METAL=OFF
-		export GGML_NO_ACCELERATE=1
-		export GGML_NO_METAL=1
+		CMAKE_ARGS+=-DLLAMA_METAL=OFF
+		export LLAMA_NO_ACCELERATE=1
 	endif

 	ifeq ($(BUILD_TYPE),metal)
 #			-lcblas 	removed: it seems to always be listed as a duplicate flag.
 		CGO_LDFLAGS += -framework Accelerate
 	endif
-else
-CGO_LDFLAGS_WHISPER+=-lgomp
 endif

 ifeq ($(BUILD_TYPE),openblas)
 	CGO_LDFLAGS+=-lopenblas
-	export GGML_OPENBLAS=1
+	export WHISPER_OPENBLAS=1
 endif

+
 ifeq ($(BUILD_TYPE),cublas)
 	CGO_LDFLAGS+=-lcublas -lcudart -L$(CUDA_LIBPATH)
-	export GGML_CUDA=1
+	export LLAMA_CUBLAS=1
+	export WHISPER_CUDA=1
 	CGO_LDFLAGS_WHISPER+=-L$(CUDA_LIBPATH)/stubs/ -lcuda -lcufft
 endif

-ifeq ($(BUILD_TYPE),vulkan)
-	CMAKE_ARGS+=-DGGML_VULKAN=1
-endif
-
-ifneq (,$(findstring sycl,$(BUILD_TYPE)))
-	export GGML_SYCL=1
-endif
-
-ifeq ($(BUILD_TYPE),sycl_f16)
-	export GGML_SYCL_F16=1
-endif
-
 ifeq ($(BUILD_TYPE),hipblas)
 	ROCM_HOME ?= /opt/rocm
 	ROCM_PATH ?= /opt/rocm
@@ -128,26 +111,27 @@ ifeq ($(BUILD_TYPE),hipblas)
 	export CC=$(ROCM_HOME)/llvm/bin/clang
 	# llama-ggml has no hipblas support, so override it here.
 	export STABLE_BUILD_TYPE=
-	export GGML_HIPBLAS=1
+	export WHISPER_HIPBLAS=1
 	GPU_TARGETS ?= gfx900,gfx906,gfx908,gfx940,gfx941,gfx942,gfx90a,gfx1030,gfx1031,gfx1100,gfx1101
 	AMDGPU_TARGETS ?= "$(GPU_TARGETS)"
-	CMAKE_ARGS+=-DGGML_HIPBLAS=ON -DAMDGPU_TARGETS="$(AMDGPU_TARGETS)" -DGPU_TARGETS="$(GPU_TARGETS)"
+	CMAKE_ARGS+=-DLLAMA_HIPBLAS=ON -DAMDGPU_TARGETS="$(AMDGPU_TARGETS)" -DGPU_TARGETS="$(GPU_TARGETS)"
 	CGO_LDFLAGS += -O3 --rtlib=compiler-rt -unwindlib=libgcc -lhipblas -lrocblas --hip-link -L${ROCM_HOME}/lib/llvm/lib
 endif

 ifeq ($(BUILD_TYPE),metal)
 	CGO_LDFLAGS+=-framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
-	export GGML_METAL=1
+	export LLAMA_METAL=1
+	export WHISPER_METAL=1
 endif

 ifeq ($(BUILD_TYPE),clblas)
 	CGO_LDFLAGS+=-lOpenCL -lclblast
-	export GGML_OPENBLAS=1
+	export WHISPER_CLBLAST=1
 endif

 # glibc-static or glibc-devel-static required
 ifeq ($(STATIC),true)
-	LD_FLAGS+=-linkmode external -extldflags -static
+	LD_FLAGS=-linkmode external -extldflags -static
 endif

 ifeq ($(findstring stablediffusion,$(GO_TAGS)),stablediffusion)
@@ -181,8 +165,6 @@ ALL_GRPC_BACKENDS+=backend-assets/grpc/rwkv
 ALL_GRPC_BACKENDS+=backend-assets/grpc/whisper
 ALL_GRPC_BACKENDS+=backend-assets/grpc/local-store
 ALL_GRPC_BACKENDS+=$(OPTIONAL_GRPC)
-# Use filter-out to remove the specified backends
-ALL_GRPC_BACKENDS := $(filter-out $(SKIP_GRPC_BACKEND),$(ALL_GRPC_BACKENDS))

 GRPC_BACKENDS?=$(ALL_GRPC_BACKENDS) $(OPTIONAL_GRPC)
 TEST_PATHS?=./api/... ./pkg/... ./core/...
@@ -262,7 +244,7 @@ sources/whisper.cpp:
 	cd sources/whisper.cpp && git checkout -b build $(WHISPER_CPP_VERSION) && git submodule update --init --recursive --depth 1

 sources/whisper.cpp/libwhisper.a: sources/whisper.cpp
-	cd sources/whisper.cpp && $(MAKE) libwhisper.a libggml.a
+	cd sources/whisper.cpp && $(MAKE) libwhisper.a

 get-sources: sources/go-llama.cpp sources/gpt4all sources/go-piper sources/go-rwkv.cpp sources/whisper.cpp sources/go-bert.cpp sources/go-stable-diffusion sources/go-tiny-dream

@@ -331,10 +313,6 @@ build: prepare backend-assets grpcs ## Build the project
 	$(info ${GREEN}I BUILD_TYPE: ${YELLOW}$(BUILD_TYPE)${RESET})
 	$(info ${GREEN}I GO_TAGS: ${YELLOW}$(GO_TAGS)${RESET})
 	$(info ${GREEN}I LD_FLAGS: ${YELLOW}$(LD_FLAGS)${RESET})
-ifneq ($(BACKEND_LIBS),)
-	$(MAKE) backend-assets/lib
-	cp -f $(BACKEND_LIBS) backend-assets/lib/
-endif
 	CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o $(BINARY_NAME) ./

 build-minimal:
@@ -343,14 +321,8 @@ build-minimal:
 build-api:
 	BUILD_GRPC_FOR_BACKEND_LLAMA=true BUILD_API_ONLY=true GO_TAGS=none $(MAKE) build

-backend-assets/lib:
-	mkdir -p backend-assets/lib
-
 dist:
-	$(MAKE) backend-assets/grpc/llama-cpp-avx2
-ifeq ($(DETECT_LIBS),true)
-	scripts/prepare-libs.sh backend-assets/grpc/llama-cpp-avx2
-endif
+	STATIC=true $(MAKE) backend-assets/grpc/llama-cpp-avx2
 ifeq ($(OS),Darwin)
 	$(info ${GREEN}I Skip CUDA/hipblas build on MacOS${RESET})
 else
@@ -359,11 +331,7 @@ else
 	$(MAKE) backend-assets/grpc/llama-cpp-sycl_f16
 	$(MAKE) backend-assets/grpc/llama-cpp-sycl_f32
 endif
-	GO_TAGS="tts p2p" $(MAKE) build
-ifeq ($(DETECT_LIBS),true)
-	scripts/prepare-libs.sh backend-assets/grpc/piper
-endif
-	GO_TAGS="tts p2p" STATIC=true $(MAKE) build
+	$(MAKE) build
 	mkdir -p release
 # if BUILD_ID is empty, then we don't append it to the binary name
 ifeq ($(BUILD_ID),)
@@ -374,9 +342,9 @@ else
 	shasum -a 256 release/$(BINARY_NAME)-$(BUILD_ID)-$(OS)-$(ARCH) > release/$(BINARY_NAME)-$(BUILD_ID)-$(OS)-$(ARCH).sha256
 endif

-dist-cross-linux-arm64:
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_NATIVE=off" GRPC_BACKENDS="backend-assets/grpc/llama-cpp-fallback backend-assets/grpc/llama-cpp-grpc backend-assets/util/llama-cpp-rpc-server" \
-	STATIC=true $(MAKE) build
+dist-cross-linux-arm64: 
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_NATIVE=off" GRPC_BACKENDS="backend-assets/grpc/llama-cpp-fallback backend-assets/grpc/llama-cpp-grpc backend-assets/util/llama-cpp-rpc-server" \
+	$(MAKE) build
 	mkdir -p release
 # if BUILD_ID is empty, then we don't append it to the binary name
 ifeq ($(BUILD_ID),)
@@ -425,7 +393,7 @@ prepare-e2e:
 	mkdir -p $(TEST_DIR)
 	cp -rfv $(abspath ./tests/e2e-fixtures)/gpu.yaml $(TEST_DIR)/gpu.yaml
 	test -e $(TEST_DIR)/ggllm-test-model.bin || wget -q https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q2_K.gguf -O $(TEST_DIR)/ggllm-test-model.bin
-	docker build --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=4 --build-arg FFMPEG=true -t localai-tests .
+	docker build --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=11 --build-arg CUDA_MINOR_VERSION=7 --build-arg FFMPEG=true -t localai-tests .

 run-e2e-image:
 	ls -liah $(abspath ./tests/e2e-fixtures)
@@ -732,21 +700,21 @@ backend-assets/grpc/llama-cpp-avx2: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-avx2
 	$(MAKE) -C backend/cpp/llama-avx2 purge
 	$(info ${GREEN}I llama-cpp build info:avx2${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-avx2" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_AVX=on -DLLAMA_AVX2=on -DLLAMA_AVX512=off -DLLAMA_FMA=on -DLLAMA_F16C=on" $(MAKE) VARIANT="llama-avx2" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-avx2/grpc-server backend-assets/grpc/llama-cpp-avx2

 backend-assets/grpc/llama-cpp-avx: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-avx
 	$(MAKE) -C backend/cpp/llama-avx purge
 	$(info ${GREEN}I llama-cpp build info:avx${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off" $(MAKE) VARIANT="llama-avx" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off" $(MAKE) VARIANT="llama-avx" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-avx/grpc-server backend-assets/grpc/llama-cpp-avx

 backend-assets/grpc/llama-cpp-fallback: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-fallback
 	$(MAKE) -C backend/cpp/llama-fallback purge
 	$(info ${GREEN}I llama-cpp build info:fallback${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off" $(MAKE) VARIANT="llama-fallback" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_AVX=off -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off" $(MAKE) VARIANT="llama-fallback" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-fallback/grpc-server backend-assets/grpc/llama-cpp-fallback
 # TODO: every binary should have its own folder instead, so can have different metal implementations
 ifeq ($(BUILD_TYPE),metal)
@@ -757,7 +725,7 @@ backend-assets/grpc/llama-cpp-cuda: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-cuda
 	$(MAKE) -C backend/cpp/llama-cuda purge
 	$(info ${GREEN}I llama-cpp build info:cuda${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_CUDA=ON" $(MAKE) VARIANT="llama-cuda" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off -DLLAMA_CUDA=ON" $(MAKE) VARIANT="llama-cuda" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-cuda/grpc-server backend-assets/grpc/llama-cpp-cuda

 backend-assets/grpc/llama-cpp-hipblas: backend-assets/grpc
@@ -785,7 +753,7 @@ backend-assets/grpc/llama-cpp-grpc: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-grpc
 	$(MAKE) -C backend/cpp/llama-grpc purge
 	$(info ${GREEN}I llama-cpp build info:grpc${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_RPC=ON -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off" TARGET="--target grpc-server --target rpc-server" $(MAKE) VARIANT="llama-grpc" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_RPC=ON -DLLAMA_AVX=off -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off" $(MAKE) VARIANT="llama-grpc" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-grpc/grpc-server backend-assets/grpc/llama-cpp-grpc

 backend-assets/util/llama-cpp-rpc-server: backend-assets/grpc/llama-cpp-grpc
@@ -813,7 +781,7 @@ backend-assets/grpc/tinydream: sources/go-tiny-dream sources/go-tiny-dream/libti
 	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/tinydream ./backend/go/image/tinydream

 backend-assets/grpc/whisper: sources/whisper.cpp sources/whisper.cpp/libwhisper.a backend-assets/grpc
-	CGO_LDFLAGS="$(CGO_LDFLAGS) $(CGO_LDFLAGS_WHISPER)" C_INCLUDE_PATH="$(CURDIR)/sources/whisper.cpp/include:$(CURDIR)/sources/whisper.cpp/ggml/include" LIBRARY_PATH=$(CURDIR)/sources/whisper.cpp \
+	CGO_LDFLAGS="$(CGO_LDFLAGS) $(CGO_LDFLAGS_WHISPER)" C_INCLUDE_PATH=$(CURDIR)/sources/whisper.cpp LIBRARY_PATH=$(CURDIR)/sources/whisper.cpp \
 	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/whisper ./backend/go/transcribe/

 backend-assets/grpc/local-store: backend-assets/grpc
@@ -835,17 +803,6 @@ docker:
 		--build-arg BUILD_TYPE=$(BUILD_TYPE) \
 		-t $(DOCKER_IMAGE) .

-docker-cuda11:
-	docker build \
-		--build-arg CUDA_MAJOR_VERSION=11 \
-		--build-arg CUDA_MINOR_VERSION=8 \
-		--build-arg BASE_IMAGE=$(BASE_IMAGE) \
-		--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
-		--build-arg GO_TAGS="$(GO_TAGS)" \
-		--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
-		--build-arg BUILD_TYPE=$(BUILD_TYPE) \
-		-t $(DOCKER_IMAGE)-cuda11 .
-
 docker-aio:
 	@echo "Building AIO image with base $(BASE_IMAGE) as $(DOCKER_AIO_IMAGE)"
 	docker build \
@@ -882,7 +839,7 @@ gen-assets:
 	$(GOCMD) run core/dependencies_manager/manager.go embedded/webui_static.yaml core/http/static/assets

 ## Documentation
-docs/layouts/_default:
+docs/layouts/_default: 
 	mkdir -p docs/layouts/_default

 docs/static/gallery.html: docs/layouts/_default
@@ -897,4 +854,4 @@ docs-clean:

 .PHONY: docs
 docs: docs/static/gallery.html
-	cd docs && hugo serve
+	cd docs && hugo serve
--- a/README.md
+++ b/README.md
@@ -48,13 +48,6 @@

 ![screen](https://github.com/mudler/LocalAI/assets/2420543/20b5ccd2-8393-44f0-aaf6-87a23806381e)

-Run the installer script:
-
-```bash
-curl https://localai.io/install.sh | sh
-```
-
-Or run with docker:
 ```bash
 docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu
 # Alternative images:
@@ -72,8 +65,6 @@ docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu

 [Roadmap](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)

- 🔥🔥 🆕 P2P Dashboard, LocalAI Federated mode and AI Swarms: https://github.com/mudler/LocalAI/pull/2723
- 🆕 You can browse now the model gallery without LocalAI! Check out https://models.localai.io
 - 🔥🔥 Decentralized llama.cpp:  https://github.com/mudler/LocalAI/pull/2343 (peer2peer llama.cpp!) 👉 Docs  https://localai.io/features/distribute/
 - 🔥🔥 Openvoice: https://github.com/mudler/LocalAI/pull/2334
 - 🆕 Function calls without grammars and mixed mode: https://github.com/mudler/LocalAI/pull/2328
@@ -105,7 +96,6 @@ If you want to help and contribute, issues up for grabs: https://github.com/mudl
 - 🥽 [Vision API](https://localai.io/features/gpt-vision/)
 - 📈 [Reranker API](https://localai.io/features/reranker/)
 - 🆕🖧 [P2P Inferencing](https://localai.io/features/distribute/)
- 🌍 Integrated WebUI!

 ## 💻 Usage

--- a/backend/backend.proto
+++ b/backend/backend.proto
@@ -230,7 +230,6 @@ message TranscriptRequest {
  string dst = 2;
  string language = 3;
  uint32 threads = 4;
-  bool translate = 5;
 }

 message TranscriptResult {
--- a/backend/cpp/llama/CMakeLists.txt
+++ b/backend/cpp/llama/CMakeLists.txt
@@ -22,15 +22,6 @@ set(TARGET grpc-server)
 set(_PROTOBUF_LIBPROTOBUF libprotobuf)
 set(_REFLECTION grpc++_reflection)

-include(FetchContent)
-FetchContent_Declare(
-  googletest
-  URL https://github.com/google/googletest/archive/03597a01ee50ed33e9dfd640b249b4be3799d395.zip
-)
-# For Windows: Prevent overriding the parent project's compiler/linker settings
-set(gtest_force_shared_crt ON CACHE BOOL "" FORCE)
-FetchContent_MakeAvailable(googletest)
-
 if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
    # Set correct Homebrew install folder for Apple Silicon and Intel Macs
    if (CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "arm64")
--- a/backend/cpp/llama/Makefile
+++ b/backend/cpp/llama/Makefile
@@ -4,44 +4,34 @@ LLAMA_VERSION?=
 CMAKE_ARGS?=
 BUILD_TYPE?=
 ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
-TARGET?=--target grpc-server

-# Disable Shared libs as we are linking on static gRPC and we can't mix shared and static
-CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
-
-# If build type is cublas, then we set -DGGML_CUDA=ON to CMAKE_ARGS automatically
+# If build type is cublas, then we set -DLLAMA_CUBLAS=ON to CMAKE_ARGS automatically
 ifeq ($(BUILD_TYPE),cublas)
-	CMAKE_ARGS+=-DGGML_CUDA=ON
-# If build type is openblas then we set -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+	CMAKE_ARGS+=-DLLAMA_CUBLAS=ON
+# If build type is openblas then we set -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
 # to CMAKE_ARGS automatically
 else ifeq ($(BUILD_TYPE),openblas)
-	CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
-# If build type is clblas (openCL) we set -DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
+	CMAKE_ARGS+=-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
+# If build type is clblas (openCL) we set -DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
 else ifeq ($(BUILD_TYPE),clblas)
-	CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
+	CMAKE_ARGS+=-DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
 # If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++ 
 else ifeq ($(BUILD_TYPE),hipblas)
-	CMAKE_ARGS+=-DGGML_HIPBLAS=ON
-# If it's OSX, DO NOT embed the metal library - -DGGML_METAL_EMBED_LIBRARY=ON requires further investigation
+	CMAKE_ARGS+=-DLLAMA_HIPBLAS=ON
+# If it's OSX, DO NOT embed the metal library - -DLLAMA_METAL_EMBED_LIBRARY=ON requires further investigation
 # But if it's OSX without metal, disable it here
-else ifeq ($(OS),Darwin)
+else ifeq ($(OS),darwin)
 	ifneq ($(BUILD_TYPE),metal)
-		CMAKE_ARGS+=-DGGML_METAL=OFF
-	else
-		CMAKE_ARGS+=-DGGML_METAL=ON
-# Until this is tested properly, we disable embedded metal file
-# as we already embed it as part of the LocalAI assets
-		CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=OFF
-		TARGET+=--target ggml-metal
+		CMAKE_ARGS+=-DLLAMA_METAL=OFF
 	endif
 endif

 ifeq ($(BUILD_TYPE),sycl_f16)
-	CMAKE_ARGS+=-DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON
+	CMAKE_ARGS+=-DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON
 endif

 ifeq ($(BUILD_TYPE),sycl_f32)
-	CMAKE_ARGS+=-DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
+	CMAKE_ARGS+=-DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
 endif

 llama.cpp:
@@ -71,9 +61,9 @@ clean: purge
 grpc-server: llama.cpp llama.cpp/examples/grpc-server
 	@echo "Building grpc-server with $(BUILD_TYPE) build type and $(CMAKE_ARGS)"
 ifneq (,$(findstring sycl,$(BUILD_TYPE)))
-	+bash -c "source $(ONEAPI_VARS); \
-	cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release $(TARGET)"
+	bash -c "source $(ONEAPI_VARS); \
+	cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && $(MAKE)"
 else
-	+cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release $(TARGET)
+	cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && $(MAKE)
 endif
 	cp llama.cpp/build/bin/grpc-server .
--- a/backend/cpp/llama/grpc-server.cpp
+++ b/backend/cpp/llama/grpc-server.cpp
@@ -886,8 +886,6 @@ struct llama_server_context
            {"task_id", slot->task_id},
        });

-        LOG_TEE("sampling: \n%s\n", llama_sampling_print(slot->sparams).c_str());
-
        return true;
    }

--- a/backend/go/image/stablediffusion/main.go
+++ b/backend/go/image/stablediffusion/main.go
@@ -5,7 +5,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/image/stablediffusion/stablediffusion.go
+++ b/backend/go/image/stablediffusion/stablediffusion.go
@@ -3,9 +3,9 @@ package main
 // This is a wrapper to statisfy the GRPC service interface
 // It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
 import (
-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/stablediffusion"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/stablediffusion"
 )

 type Image struct {
--- a/backend/go/image/tinydream/main.go
+++ b/backend/go/image/tinydream/main.go
@@ -5,7 +5,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/image/tinydream/tinydream.go
+++ b/backend/go/image/tinydream/tinydream.go
@@ -3,9 +3,9 @@ package main
 // This is a wrapper to statisfy the GRPC service interface
 // It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
 import (
-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/tinydream"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/tinydream"
 )

 type Image struct {
--- a/backend/go/llm/bert/bert.go
+++ b/backend/go/llm/bert/bert.go
@@ -5,8 +5,8 @@ package main
 import (
 	bert "github.com/go-skynet/go-bert.cpp"

-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 )

 type Embeddings struct {
--- a/backend/go/llm/bert/main.go
+++ b/backend/go/llm/bert/main.go
@@ -5,7 +5,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/llm/gpt4all/gpt4all.go
+++ b/backend/go/llm/gpt4all/gpt4all.go
@@ -5,8 +5,8 @@ package main
 import (
 	"fmt"

-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	gpt4all "github.com/nomic-ai/gpt4all/gpt4all-bindings/golang"
 )

--- a/backend/go/llm/gpt4all/main.go
+++ b/backend/go/llm/gpt4all/main.go
@@ -5,7 +5,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/llm/langchain/langchain.go
+++ b/backend/go/llm/langchain/langchain.go
@@ -6,9 +6,9 @@ import (
 	"fmt"
 	"os"

-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/langchain"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/langchain"
 )

 type LLM struct {
--- a/backend/go/llm/langchain/main.go
+++ b/backend/go/llm/langchain/main.go
@@ -5,7 +5,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/llm/llama-ggml/llama.go
+++ b/backend/go/llm/llama-ggml/llama.go
@@ -5,9 +5,9 @@ package main
 import (
 	"fmt"

+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	"github.com/go-skynet/go-llama.cpp"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
 )

 type LLM struct {
--- a/backend/go/llm/llama-ggml/main.go
+++ b/backend/go/llm/llama-ggml/main.go
@@ -3,7 +3,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/llm/llama/llama.go
+++ b/backend/go/llm/llama/llama.go
@@ -6,9 +6,9 @@ import (
 	"fmt"
 	"path/filepath"

+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
 	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	"github.com/go-skynet/go-llama.cpp"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
 )

 type LLM struct {
--- a/backend/go/llm/llama/main.go
+++ b/backend/go/llm/llama/main.go
@@ -7,7 +7,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/llm/rwkv/main.go
+++ b/backend/go/llm/rwkv/main.go
@@ -5,7 +5,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/llm/rwkv/rwkv.go
+++ b/backend/go/llm/rwkv/rwkv.go
@@ -7,8 +7,8 @@ import (
 	"path/filepath"

 	"github.com/donomii/go-rwkv.cpp"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 )

 const tokenizerSuffix = ".tokenizer.json"
@@ -31,7 +31,7 @@ func (llm *LLM) Load(opts *pb.ModelOptions) error {
 	model := rwkv.LoadFiles(opts.ModelFile, tokenizerPath, uint32(opts.GetThreads()))

 	if model == nil {
-		return fmt.Errorf("rwkv could not load model")
+		return fmt.Errorf("could not load model")
 	}
 	llm.rwkv = model
 	return nil
--- a/backend/go/stores/main.go
+++ b/backend/go/stores/main.go
@@ -6,7 +6,7 @@ import (
 	"flag"
 	"os"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 )
--- a/backend/go/stores/store.go
+++ b/backend/go/stores/store.go
@@ -8,8 +8,8 @@ import (
 	"math"
 	"slices"

-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"

 	"github.com/rs/zerolog/log"
 )
--- a/backend/go/transcribe/main.go
+++ b/backend/go/transcribe/main.go
@@ -5,7 +5,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/transcribe/transcript.go
+++ b/backend/go/transcribe/transcript.go
@@ -8,7 +8,7 @@ import (

 	"github.com/ggerganov/whisper.cpp/bindings/go/pkg/whisper"
 	"github.com/go-audio/wav"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
 )

 func ffmpegCommand(args []string) (string, error) {
@@ -29,7 +29,7 @@ func audioToWav(src, dst string) error {
 	return nil
 }

-func Transcript(model whisper.Model, audiopath, language string, translate bool, threads uint) (schema.TranscriptionResult, error) {
+func Transcript(model whisper.Model, audiopath, language string, threads uint) (schema.TranscriptionResult, error) {
 	res := schema.TranscriptionResult{}

 	dir, err := os.MkdirTemp("", "whisper")
@@ -75,10 +75,6 @@ func Transcript(model whisper.Model, audiopath, language string, translate bool,
 		context.SetLanguage("auto")
 	}

-	if translate {
-		context.SetTranslate(true)
-	}
-
 	if err := context.Process(data, nil, nil); err != nil {
 		return res, err
 	}
--- a/backend/go/transcribe/whisper.go
+++ b/backend/go/transcribe/whisper.go
@@ -4,9 +4,9 @@ package main
 // It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
 import (
 	"github.com/ggerganov/whisper.cpp/bindings/go/pkg/whisper"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 )

 type Whisper struct {
@@ -22,5 +22,5 @@ func (sd *Whisper) Load(opts *pb.ModelOptions) error {
 }

 func (sd *Whisper) AudioTranscription(opts *pb.TranscriptRequest) (schema.TranscriptionResult, error) {
-	return Transcript(sd.whisper, opts.Dst, opts.Language, opts.Translate, uint(opts.Threads))
+	return Transcript(sd.whisper, opts.Dst, opts.Language, uint(opts.Threads))
 }
--- a/backend/go/tts/main.go
+++ b/backend/go/tts/main.go
@@ -5,7 +5,7 @@ package main
 import (
 	"flag"

-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

 var (
--- a/backend/go/tts/piper.go
+++ b/backend/go/tts/piper.go
@@ -7,8 +7,8 @@ import (
 	"os"
 	"path/filepath"

-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	piper "github.com/mudler/go-piper"
 )

--- a/backend/python/common/libbackend.sh
+++ b/backend/python/common/libbackend.sh
@@ -148,13 +148,13 @@ function startBackend() {
    ensureVenv

    if [ ! -z ${BACKEND_FILE} ]; then
-        exec python ${BACKEND_FILE} $@
+        python ${BACKEND_FILE} $@
    elif [ -e "${MY_DIR}/server.py" ]; then
-        exec python ${MY_DIR}/server.py $@
+        python ${MY_DIR}/server.py $@
    elif [ -e "${MY_DIR}/backend.py" ]; then
-        exec python ${MY_DIR}/backend.py $@
+        python ${MY_DIR}/backend.py $@
    elif [ -e "${MY_DIR}/${BACKEND_NAME}.py" ]; then
-        exec python ${MY_DIR}/${BACKEND_NAME}.py $@
+        python ${MY_DIR}/${BACKEND_NAME}.py $@
    fi
 }

@@ -210,4 +210,4 @@ function checkTargets() {
    echo false
 }

-init
+init
--- a/backend/python/diffusers/backend.py
+++ b/backend/python/diffusers/backend.py
@@ -17,7 +17,7 @@ import backend_pb2_grpc

 import grpc

-from diffusers import StableDiffusion3Pipeline, StableDiffusionXLPipeline, StableDiffusionDepth2ImgPipeline, DPMSolverMultistepScheduler, StableDiffusionPipeline, DiffusionPipeline, EulerAncestralDiscreteScheduler
+from diffusers import StableDiffusionXLPipeline, StableDiffusionDepth2ImgPipeline, DPMSolverMultistepScheduler, StableDiffusionPipeline, DiffusionPipeline, EulerAncestralDiscreteScheduler
 from diffusers import StableDiffusionImg2ImgPipeline, AutoPipelineForText2Image, ControlNetModel, StableVideoDiffusionPipeline
 from diffusers.pipelines.stable_diffusion import safety_checker
 from diffusers.utils import load_image,export_to_video
@@ -225,17 +225,6 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                        torch_dtype=torchType, 
                        use_safetensors=True, 
                        variant=variant)
-            elif request.PipelineType == "StableDiffusion3Pipeline":
-                if fromSingleFile:
-                    self.pipe = StableDiffusion3Pipeline.from_single_file(modelFile,
-                                                               torch_dtype=torchType,
-                                                               use_safetensors=True)
-                else:
-                    self.pipe = StableDiffusion3Pipeline.from_pretrained(
-                        request.Model, 
-                        torch_dtype=torchType, 
-                        use_safetensors=True, 
-                        variant=variant)

            if CLIPSKIP and request.CLIPSkip != 0:
                self.clip_skip = request.CLIPSkip
--- a/backend/python/diffusers/requirements.txt
+++ b/backend/python/diffusers/requirements.txt
@@ -5,7 +5,6 @@ grpcio==1.64.0
 opencv-python
 pillow
 protobuf
-sentencepiece
 torch
 transformers
-certifi
+certifi
--- a/core/application.go
+++ b/core/application.go
@@ -1,9 +1,9 @@
 package core

 import (
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/model"
 )

 // The purpose of this structure is to hold pointers to all initialized services, to make plumbing easy
@@ -28,6 +28,7 @@ type Application struct {
 	// LocalAI System Services
 	BackendMonitorService *services.BackendMonitorService
 	GalleryService        *services.GalleryService
+	ListModelsService     *services.ListModelsService
 	LocalAIMetricsService *services.LocalAIMetricsService
 	// OpenAIService         *services.OpenAIService
 }
--- a/core/backend/embeddings.go
+++ b/core/backend/embeddings.go
@@ -3,10 +3,10 @@ package backend
 import (
 	"fmt"

-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"

-	"github.com/mudler/LocalAI/pkg/grpc"
-	model "github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/grpc"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )

 func ModelEmbedding(s string, tokens []int, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (func() ([]float32, error), error) {
--- a/core/backend/image.go
+++ b/core/backend/image.go
@@ -1,10 +1,10 @@
 package backend

 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"

-	"github.com/mudler/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )

 func ImageGeneration(height, width, mode, step, seed int, positive_prompt, negative_prompt, src, dst string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (func() error, error) {
--- a/core/backend/llm.go
+++ b/core/backend/llm.go
@@ -9,14 +9,14 @@ import (
 	"sync"
 	"unicode/utf8"

-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"

-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/pkg/grpc"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/grpc"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	model "github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 )

 type LLMResponse struct {
@@ -57,7 +57,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
 		if _, err := os.Stat(modelFile); os.IsNotExist(err) {
 			utils.ResetDownloadTimers()
 			// if we failed to load the model, we try to download it
-			err := gallery.InstallModelFromGallery(o.Galleries, modelFile, loader.ModelPath, gallery.GalleryModel{}, utils.DisplayDownloadFunction, o.EnforcePredownloadScans)
+			err := gallery.InstallModelFromGallery(o.Galleries, modelFile, loader.ModelPath, gallery.GalleryModel{}, utils.DisplayDownloadFunction)
 			if err != nil {
 				return nil, err
 			}
--- a/core/backend/options.go
+++ b/core/backend/options.go
@@ -5,9 +5,9 @@ import (
 	"os"
 	"path/filepath"

-	"github.com/mudler/LocalAI/core/config"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/config"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )

@@ -142,14 +142,12 @@ func gRPCPredictOpts(c config.BackendConfig, modelPath string) *pb.PredictOption
 		MirostatTAU:         float32(*c.LLMConfig.MirostatTAU),
 		Debug:               *c.Debug,
 		StopPrompts:         c.StopWords,
-		Repeat:              int32(c.RepeatLastN),
-		FrequencyPenalty:    float32(c.FrequencyPenalty),
-		PresencePenalty:     float32(c.PresencePenalty),
-		Penalty:             float32(c.RepeatPenalty),
+		Repeat:              int32(c.RepeatPenalty),
 		NKeep:               int32(c.Keep),
 		Batch:               int32(c.Batch),
 		IgnoreEOS:           c.IgnoreEOS,
 		Seed:                getSeed(c),
+		FrequencyPenalty:    float32(c.FrequencyPenalty),
 		MLock:               *c.MMlock,
 		MMap:                *c.MMap,
 		MainGPU:             c.MainGPU,
--- a/core/backend/rerank.go
+++ b/core/backend/rerank.go
@@ -4,9 +4,9 @@ import (
 	"context"
 	"fmt"

-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )

 func Rerank(backend, modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {
--- a/core/backend/stores.go
+++ b/core/backend/stores.go
@@ -1,10 +1,10 @@
 package backend

 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"

-	"github.com/mudler/LocalAI/pkg/grpc"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/grpc"
+	"github.com/go-skynet/LocalAI/pkg/model"
 )

 func StoreBackend(sl *model.ModelLoader, appConfig *config.ApplicationConfig, storeName string) (grpc.Backend, error) {
--- a/core/backend/transcript.go
+++ b/core/backend/transcript.go
@@ -4,14 +4,14 @@ import (
 	"context"
 	"fmt"

-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"

-	"github.com/mudler/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )

-func ModelTranscription(audio, language string, translate bool, ml *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (*schema.TranscriptionResult, error) {
+func ModelTranscription(audio, language string, ml *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (*schema.TranscriptionResult, error) {

 	opts := modelOpts(backendConfig, appConfig, []model.Option{
 		model.WithBackendString(model.WhisperBackend),
@@ -31,9 +31,8 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 	}

 	return whisperModel.AudioTranscription(context.Background(), &proto.TranscriptRequest{
-		Dst:       audio,
-		Language:  language,
-		Translate: translate,
-		Threads:   uint32(*backendConfig.Threads),
+		Dst:      audio,
+		Language: language,
+		Threads:  uint32(*backendConfig.Threads),
 	})
 }
--- a/core/backend/tts.go
+++ b/core/backend/tts.go
@@ -6,11 +6,11 @@ import (
 	"os"
 	"path/filepath"

-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"

-	"github.com/mudler/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	model "github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 )

 func generateUniqueFileName(dir, baseName, ext string) string {
--- a/core/cli/cli.go
+++ b/core/cli/cli.go
@@ -1,15 +1,14 @@
 package cli

 import (
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/cli/worker"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
+	"github.com/go-skynet/LocalAI/core/cli/worker"
 )

 var CLI struct {
 	cliContext.Context `embed:""`

 	Run        RunCMD        `cmd:"" help:"Run LocalAI, this the default command if no other command is specified. Run 'local-ai run --help' for more information" default:"withargs"`
-	Federated  FederatedCLI  `cmd:"" help:"Run LocalAI in federated mode"`
 	Models     ModelsCMD     `cmd:"" help:"Manage LocalAI models and definitions"`
 	TTS        TTSCMD        `cmd:"" help:"Convert text to speech"`
 	Transcript TranscriptCMD `cmd:"" help:"Convert audio to text"`
--- a/core/cli/federated.go
+++ b/core/cli/federated.go
@@ -1,130 +0,0 @@
-package cli
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"io"
-	"net"
-	"time"
-
-	"math/rand/v2"
-
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/p2p"
-	"github.com/mudler/edgevpn/pkg/node"
-	"github.com/mudler/edgevpn/pkg/protocol"
-	"github.com/mudler/edgevpn/pkg/types"
-	"github.com/rs/zerolog/log"
-)
-
-type FederatedCLI struct {
-	Address        string `env:"LOCALAI_ADDRESS,ADDRESS" default:":8080" help:"Bind address for the API server" group:"api"`
-	Peer2PeerToken string `env:"LOCALAI_P2P_TOKEN,P2P_TOKEN,TOKEN" name:"p2ptoken" help:"Token for P2P mode (optional)" group:"p2p"`
-}
-
-func (f *FederatedCLI) Run(ctx *cliContext.Context) error {
-
-	n, err := p2p.NewNode(f.Peer2PeerToken)
-	if err != nil {
-		return fmt.Errorf("creating a new node: %w", err)
-	}
-	err = n.Start(context.Background())
-	if err != nil {
-		return fmt.Errorf("creating a new node: %w", err)
-	}
-
-	if err := p2p.ServiceDiscoverer(context.Background(), n, f.Peer2PeerToken, p2p.FederatedID, nil); err != nil {
-		return err
-	}
-
-	return Proxy(context.Background(), n, f.Address, p2p.FederatedID)
-}
-
-func Proxy(ctx context.Context, node *node.Node, listenAddr, service string) error {
-
-	log.Info().Msgf("Allocating service '%s' on: %s", service, listenAddr)
-	// Open local port for listening
-	l, err := net.Listen("tcp", listenAddr)
-	if err != nil {
-		log.Error().Err(err).Msg("Error listening")
-		return err
-	}
-	//	ll.Info("Binding local port on", srcaddr)
-
-	ledger, _ := node.Ledger()
-
-	// Announce ourselves so nodes accepts our connection
-	ledger.Announce(
-		ctx,
-		10*time.Second,
-		func() {
-			// Retrieve current ID for ip in the blockchain
-			//_, found := ledger.GetKey(protocol.UsersLedgerKey, node.Host().ID().String())
-			// If mismatch, update the blockchain
-			//if !found {
-			updatedMap := map[string]interface{}{}
-			updatedMap[node.Host().ID().String()] = &types.User{
-				PeerID:    node.Host().ID().String(),
-				Timestamp: time.Now().String(),
-			}
-			ledger.Add(protocol.UsersLedgerKey, updatedMap)
-			//	}
-		},
-	)
-
-	defer l.Close()
-	for {
-		select {
-		case <-ctx.Done():
-			return errors.New("context canceled")
-		default:
-			log.Debug().Msg("New for connection")
-			// Listen for an incoming connection.
-			conn, err := l.Accept()
-			if err != nil {
-				fmt.Println("Error accepting: ", err.Error())
-				continue
-			}
-
-			// Handle connections in a new goroutine, forwarding to the p2p service
-			go func() {
-				var tunnelAddresses []string
-				for _, v := range p2p.GetAvailableNodes(p2p.FederatedID) {
-					if v.IsOnline() {
-						tunnelAddresses = append(tunnelAddresses, v.TunnelAddress)
-					} else {
-						log.Info().Msgf("Node %s is offline", v.ID)
-					}
-				}
-
-				// open a TCP stream to one of the tunnels
-				// chosen randomly
-				// TODO: optimize this and track usage
-				tunnelAddr := tunnelAddresses[rand.IntN(len(tunnelAddresses))]
-
-				tunnelConn, err := net.Dial("tcp", tunnelAddr)
-				if err != nil {
-					log.Error().Err(err).Msg("Error connecting to tunnel")
-					return
-				}
-
-				log.Info().Msgf("Redirecting %s to %s", conn.LocalAddr().String(), tunnelConn.RemoteAddr().String())
-				closer := make(chan struct{}, 2)
-				go copyStream(closer, tunnelConn, conn)
-				go copyStream(closer, conn, tunnelConn)
-				<-closer
-
-				tunnelConn.Close()
-				conn.Close()
-				//	ll.Infof("(service %s) Done handling %s", serviceID, l.Addr().String())
-			}()
-		}
-	}
-
-}
-
-func copyStream(closer chan struct{}, dst io.Writer, src io.Reader) {
-	defer func() { closer <- struct{}{} }() // connection is closed, send signal to stop proxy
-	io.Copy(dst, src)
-}
--- a/core/cli/models.go
+++ b/core/cli/models.go
@@ -2,15 +2,12 @@ package cli

 import (
 	"encoding/json"
-	"errors"
 	"fmt"

-	cliContext "github.com/mudler/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"

-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/startup"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/startup"
 	"github.com/rs/zerolog/log"
 	"github.com/schollz/progressbar/v3"
 )
@@ -25,8 +22,7 @@ type ModelsList struct {
 }

 type ModelsInstall struct {
-	DisablePredownloadScan bool     `env:"LOCALAI_DISABLE_PREDOWNLOAD_SCAN" help:"If true, disables the best-effort security scanner before downloading any files." group:"hardening" default:"false"`
-	ModelArgs              []string `arg:"" optional:"" name:"models" help:"Model configuration URLs to load"`
+	ModelArgs []string `arg:"" optional:"" name:"models" help:"Model configuration URLs to load"`

 	ModelsCMDFlags `embed:""`
 }
@@ -37,7 +33,7 @@ type ModelsCMD struct {
 }

 func (ml *ModelsList) Run(ctx *cliContext.Context) error {
-	var galleries []config.Gallery
+	var galleries []gallery.Gallery
 	if err := json.Unmarshal([]byte(ml.Galleries), &galleries); err != nil {
 		log.Error().Err(err).Msg("unable to load galleries")
 	}
@@ -57,11 +53,10 @@ func (ml *ModelsList) Run(ctx *cliContext.Context) error {
 }

 func (mi *ModelsInstall) Run(ctx *cliContext.Context) error {
-	var galleries []config.Gallery
+	var galleries []gallery.Gallery
 	if err := json.Unmarshal([]byte(mi.Galleries), &galleries); err != nil {
 		log.Error().Err(err).Msg("unable to load galleries")
 	}
-
 	for _, modelName := range mi.ModelArgs {

 		progressBar := progressbar.NewOptions(
@@ -83,22 +78,14 @@ func (mi *ModelsInstall) Run(ctx *cliContext.Context) error {
 			return err
 		}

-		if !downloader.LooksLikeOCI(modelName) {
-			model := gallery.FindModel(models, modelName, mi.ModelsPath)
-			if model == nil {
-				log.Error().Str("model", modelName).Msg("model not found")
-				return err
-			}
-
-			err = gallery.SafetyScanGalleryModel(model)
-			if err != nil && !errors.Is(err, downloader.ErrNonHuggingFaceFile) {
-				return err
-			}
-
-			log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
+		model := gallery.FindModel(models, modelName, mi.ModelsPath)
+		if model == nil {
+			log.Error().Str("model", modelName).Msg("model not found")
+			return err
 		}

-		err = startup.InstallModels(galleries, "", mi.ModelsPath, !mi.DisablePredownloadScan, progressCallback, modelName)
+		log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
+		err = startup.InstallModels(galleries, "", mi.ModelsPath, progressCallback, modelName)
 		if err != nil {
 			return err
 		}
--- a/core/cli/run.go
+++ b/core/cli/run.go
@@ -3,16 +3,14 @@ package cli
 import (
 	"context"
 	"fmt"
-	"net"
-	"os"
 	"strings"
 	"time"

-	cliContext "github.com/mudler/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http"
-	"github.com/mudler/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/core/startup"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http"
+	"github.com/go-skynet/LocalAI/core/p2p"
+	"github.com/go-skynet/LocalAI/core/startup"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 )
@@ -42,27 +40,24 @@ type RunCMD struct {
 	Threads     int  `env:"LOCALAI_THREADS,THREADS" short:"t" help:"Number of threads used for parallel computation. Usage of the number of physical cores in the system is suggested" group:"performance"`
 	ContextSize int  `env:"LOCALAI_CONTEXT_SIZE,CONTEXT_SIZE" default:"512" help:"Default context size for models" group:"performance"`

-	Address                string   `env:"LOCALAI_ADDRESS,ADDRESS" default:":8080" help:"Bind address for the API server" group:"api"`
-	CORS                   bool     `env:"LOCALAI_CORS,CORS" help:"" group:"api"`
-	CORSAllowOrigins       string   `env:"LOCALAI_CORS_ALLOW_ORIGINS,CORS_ALLOW_ORIGINS" group:"api"`
-	LibraryPath            string   `env:"LOCALAI_LIBRARY_PATH,LIBRARY_PATH" help:"Path to the library directory (for e.g. external libraries used by backends)" default:"/usr/share/local-ai/libs" group:"backends"`
-	CSRF                   bool     `env:"LOCALAI_CSRF" help:"Enables fiber CSRF middleware" group:"api"`
-	UploadLimit            int      `env:"LOCALAI_UPLOAD_LIMIT,UPLOAD_LIMIT" default:"15" help:"Default upload-limit in MB" group:"api"`
-	APIKeys                []string `env:"LOCALAI_API_KEY,API_KEY" help:"List of API Keys to enable API authentication. When this is set, all the requests must be authenticated with one of these API keys" group:"api"`
-	DisableWebUI           bool     `env:"LOCALAI_DISABLE_WEBUI,DISABLE_WEBUI" default:"false" help:"Disable webui" group:"api"`
-	DisablePredownloadScan bool     `env:"LOCALAI_DISABLE_PREDOWNLOAD_SCAN" help:"If true, disables the best-effort security scanner before downloading any files." group:"hardening" default:"false"`
-	OpaqueErrors           bool     `env:"LOCALAI_OPAQUE_ERRORS" default:"false" help:"If true, all error responses are replaced with blank 500 errors. This is intended only for hardening against information leaks and is normally not recommended." group:"hardening"`
-	Peer2Peer              bool     `env:"LOCALAI_P2P,P2P" name:"p2p" default:"false" help:"Enable P2P mode" group:"p2p"`
-	Peer2PeerToken         string   `env:"LOCALAI_P2P_TOKEN,P2P_TOKEN,TOKEN" name:"p2ptoken" help:"Token for P2P mode (optional)" group:"p2p"`
-	ParallelRequests       bool     `env:"LOCALAI_PARALLEL_REQUESTS,PARALLEL_REQUESTS" help:"Enable backends to handle multiple requests in parallel if they support it (e.g.: llama.cpp or vllm)" group:"backends"`
-	SingleActiveBackend    bool     `env:"LOCALAI_SINGLE_ACTIVE_BACKEND,SINGLE_ACTIVE_BACKEND" help:"Allow only one backend to be run at a time" group:"backends"`
-	PreloadBackendOnly     bool     `env:"LOCALAI_PRELOAD_BACKEND_ONLY,PRELOAD_BACKEND_ONLY" default:"false" help:"Do not launch the API services, only the preloaded models / backends are started (useful for multi-node setups)" group:"backends"`
-	ExternalGRPCBackends   []string `env:"LOCALAI_EXTERNAL_GRPC_BACKENDS,EXTERNAL_GRPC_BACKENDS" help:"A list of external grpc backends" group:"backends"`
-	EnableWatchdogIdle     bool     `env:"LOCALAI_WATCHDOG_IDLE,WATCHDOG_IDLE" default:"false" help:"Enable watchdog for stopping backends that are idle longer than the watchdog-idle-timeout" group:"backends"`
-	WatchdogIdleTimeout    string   `env:"LOCALAI_WATCHDOG_IDLE_TIMEOUT,WATCHDOG_IDLE_TIMEOUT" default:"15m" help:"Threshold beyond which an idle backend should be stopped" group:"backends"`
-	EnableWatchdogBusy     bool     `env:"LOCALAI_WATCHDOG_BUSY,WATCHDOG_BUSY" default:"false" help:"Enable watchdog for stopping backends that are busy longer than the watchdog-busy-timeout" group:"backends"`
-	WatchdogBusyTimeout    string   `env:"LOCALAI_WATCHDOG_BUSY_TIMEOUT,WATCHDOG_BUSY_TIMEOUT" default:"5m" help:"Threshold beyond which a busy backend should be stopped" group:"backends"`
-	Federated              bool     `env:"LOCALAI_FEDERATED,FEDERATED" help:"Enable federated instance" group:"federated"`
+	Address              string   `env:"LOCALAI_ADDRESS,ADDRESS" default:":8080" help:"Bind address for the API server" group:"api"`
+	CORS                 bool     `env:"LOCALAI_CORS,CORS" help:"" group:"api"`
+	CORSAllowOrigins     string   `env:"LOCALAI_CORS_ALLOW_ORIGINS,CORS_ALLOW_ORIGINS" group:"api"`
+	CSRF                 bool     `env:"LOCALAI_CSRF" help:"Enables fiber CSRF middleware" group:"api"`
+	UploadLimit          int      `env:"LOCALAI_UPLOAD_LIMIT,UPLOAD_LIMIT" default:"15" help:"Default upload-limit in MB" group:"api"`
+	APIKeys              []string `env:"LOCALAI_API_KEY,API_KEY" help:"List of API Keys to enable API authentication. When this is set, all the requests must be authenticated with one of these API keys" group:"api"`
+	DisableWebUI         bool     `env:"LOCALAI_DISABLE_WEBUI,DISABLE_WEBUI" default:"false" help:"Disable webui" group:"api"`
+	OpaqueErrors         bool     `env:"LOCALAI_OPAQUE_ERRORS" default:"false" help:"If true, all error responses are replaced with blank 500 errors. This is intended only for hardening against information leaks and is normally not recommended." group:"api"`
+	Peer2Peer            bool     `env:"LOCALAI_P2P,P2P" name:"p2p" default:"false" help:"Enable P2P mode" group:"p2p"`
+	Peer2PeerToken       string   `env:"LOCALAI_P2P_TOKEN,P2P_TOKEN" name:"p2ptoken" help:"Token for P2P mode (optional)" group:"p2p"`
+	ParallelRequests     bool     `env:"LOCALAI_PARALLEL_REQUESTS,PARALLEL_REQUESTS" help:"Enable backends to handle multiple requests in parallel if they support it (e.g.: llama.cpp or vllm)" group:"backends"`
+	SingleActiveBackend  bool     `env:"LOCALAI_SINGLE_ACTIVE_BACKEND,SINGLE_ACTIVE_BACKEND" help:"Allow only one backend to be run at a time" group:"backends"`
+	PreloadBackendOnly   bool     `env:"LOCALAI_PRELOAD_BACKEND_ONLY,PRELOAD_BACKEND_ONLY" default:"false" help:"Do not launch the API services, only the preloaded models / backends are started (useful for multi-node setups)" group:"backends"`
+	ExternalGRPCBackends []string `env:"LOCALAI_EXTERNAL_GRPC_BACKENDS,EXTERNAL_GRPC_BACKENDS" help:"A list of external grpc backends" group:"backends"`
+	EnableWatchdogIdle   bool     `env:"LOCALAI_WATCHDOG_IDLE,WATCHDOG_IDLE" default:"false" help:"Enable watchdog for stopping backends that are idle longer than the watchdog-idle-timeout" group:"backends"`
+	WatchdogIdleTimeout  string   `env:"LOCALAI_WATCHDOG_IDLE_TIMEOUT,WATCHDOG_IDLE_TIMEOUT" default:"15m" help:"Threshold beyond which an idle backend should be stopped" group:"backends"`
+	EnableWatchdogBusy   bool     `env:"LOCALAI_WATCHDOG_BUSY,WATCHDOG_BUSY" default:"false" help:"Enable watchdog for stopping backends that are busy longer than the watchdog-busy-timeout" group:"backends"`
+	WatchdogBusyTimeout  string   `env:"LOCALAI_WATCHDOG_BUSY_TIMEOUT,WATCHDOG_BUSY_TIMEOUT" default:"5m" help:"Threshold beyond which a busy backend should be stopped" group:"backends"`
 }

 func (r *RunCMD) Run(ctx *cliContext.Context) error {
@@ -85,7 +80,6 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 		config.WithCors(r.CORS),
 		config.WithCorsAllowOrigins(r.CORSAllowOrigins),
 		config.WithCsrf(r.CSRF),
-		config.WithLibPath(r.LibraryPath),
 		config.WithThreads(r.Threads),
 		config.WithBackendAssets(ctx.BackendAssets),
 		config.WithBackendAssetsOutput(r.BackendAssetsPath),
@@ -93,13 +87,11 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 		config.WithApiKeys(r.APIKeys),
 		config.WithModelsURL(append(r.Models, r.ModelArgs...)...),
 		config.WithOpaqueErrors(r.OpaqueErrors),
-		config.WithEnforcedPredownloadScans(!r.DisablePredownloadScan),
 	}

-	token := ""
 	if r.Peer2Peer || r.Peer2PeerToken != "" {
 		log.Info().Msg("P2P mode enabled")
-		token = r.Peer2PeerToken
+		token := r.Peer2PeerToken
 		if token == "" {
 			// IF no token is provided, and p2p is enabled,
 			// we generate one and wait for the user to pick up the token (this is for interactive)
@@ -110,46 +102,14 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {

 			log.Info().Msg("To use the token, you can run the following command in another node or terminal:")
 			fmt.Printf("export TOKEN=\"%s\"\nlocal-ai worker p2p-llama-cpp-rpc\n", token)
-		}
-		opts = append(opts, config.WithP2PToken(token))

-		node, err := p2p.NewNode(token)
-		if err != nil {
-			return err
+			// Ask for user confirmation
+			log.Info().Msg("Press a button to proceed")
+			var input string
+			fmt.Scanln(&input)
 		}
-
 		log.Info().Msg("Starting P2P server discovery...")
-		if err := p2p.ServiceDiscoverer(context.Background(), node, token, "", func() {
-			var tunnelAddresses []string
-			for _, v := range p2p.GetAvailableNodes("") {
-				if v.IsOnline() {
-					tunnelAddresses = append(tunnelAddresses, v.TunnelAddress)
-				} else {
-					log.Info().Msgf("Node %s is offline", v.ID)
-				}
-			}
-			tunnelEnvVar := strings.Join(tunnelAddresses, ",")
-
-			os.Setenv("LLAMACPP_GRPC_SERVERS", tunnelEnvVar)
-			log.Debug().Msgf("setting LLAMACPP_GRPC_SERVERS to %s", tunnelEnvVar)
-		}); err != nil {
-			return err
-		}
-	}
-
-	if r.Federated {
-		_, port, err := net.SplitHostPort(r.Address)
-		if err != nil {
-			return err
-		}
-		if err := p2p.ExposeService(context.Background(), "localhost", port, token, p2p.FederatedID); err != nil {
-			return err
-		}
-		node, err := p2p.NewNode(token)
-		if err != nil {
-			return err
-		}
-		if err := p2p.ServiceDiscoverer(context.Background(), node, token, p2p.FederatedID, nil); err != nil {
+		if err := p2p.LLamaCPPRPCServerDiscoverer(context.Background(), token); err != nil {
 			return err
 		}
 	}
--- a/core/cli/transcript.go
+++ b/core/cli/transcript.go
@@ -5,10 +5,10 @@ import (
 	"errors"
 	"fmt"

-	"github.com/mudler/LocalAI/core/backend"
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/backend"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )

@@ -18,7 +18,6 @@ type TranscriptCMD struct {
 	Backend           string `short:"b" default:"whisper" help:"Backend to run the transcription model"`
 	Model             string `short:"m" required:"" help:"Model name to run the TTS"`
 	Language          string `short:"l" help:"Language of the audio file"`
-	Translate         bool   `short:"c" help:"Translate the transcription to english"`
 	Threads           int    `short:"t" default:"1" help:"Number of threads used for parallel computation"`
 	ModelsPath        string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
 	BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
@@ -51,7 +50,7 @@ func (t *TranscriptCMD) Run(ctx *cliContext.Context) error {
 		}
 	}()

-	tr, err := backend.ModelTranscription(t.Filename, t.Language, t.Translate, ml, c, opts)
+	tr, err := backend.ModelTranscription(t.Filename, t.Language, ml, c, opts)
 	if err != nil {
 		return err
 	}
--- a/core/cli/tts.go
+++ b/core/cli/tts.go
@@ -7,10 +7,10 @@ import (
 	"path/filepath"
 	"strings"

-	"github.com/mudler/LocalAI/core/backend"
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/backend"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )

--- a/core/cli/util.go
+++ b/core/cli/util.go
@@ -1,22 +1,16 @@
 package cli

 import (
-	"encoding/json"
-	"errors"
 	"fmt"

 	"github.com/rs/zerolog/log"

-	cliContext "github.com/mudler/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/pkg/downloader"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
 	gguf "github.com/thxcode/gguf-parser-go"
 )

 type UtilCMD struct {
 	GGUFInfo GGUFInfoCMD `cmd:"" name:"gguf-info" help:"Get information about a GGUF file"`
-	HFScan   HFScanCMD   `cmd:"" name:"hf-scan" help:"Checks installed models for known security issues. WARNING: this is a best-effort feature and may not catch everything!"`
 }

 type GGUFInfoCMD struct {
@@ -24,12 +18,6 @@ type GGUFInfoCMD struct {
 	Header bool     `optional:"" default:"false" name:"header" help:"Show header information"`
 }

-type HFScanCMD struct {
-	ModelsPath string   `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
-	Galleries  string   `env:"LOCALAI_GALLERIES,GALLERIES" help:"JSON list of galleries" group:"models" default:"${galleries}"`
-	ToScan     []string `arg:""`
-}
-
 func (u *GGUFInfoCMD) Run(ctx *cliContext.Context) error {
 	if u.Args == nil || len(u.Args) == 0 {
 		return fmt.Errorf("no GGUF file provided")
@@ -65,37 +53,3 @@ func (u *GGUFInfoCMD) Run(ctx *cliContext.Context) error {

 	return nil
 }
-
-func (hfscmd *HFScanCMD) Run(ctx *cliContext.Context) error {
-	log.Info().Msg("LocalAI Security Scanner - This is BEST EFFORT functionality! Currently limited to huggingface models!")
-	if len(hfscmd.ToScan) == 0 {
-		log.Info().Msg("Checking all installed models against galleries")
-		var galleries []config.Gallery
-		if err := json.Unmarshal([]byte(hfscmd.Galleries), &galleries); err != nil {
-			log.Error().Err(err).Msg("unable to load galleries")
-		}
-
-		err := gallery.SafetyScanGalleryModels(galleries, hfscmd.ModelsPath)
-		if err == nil {
-			log.Info().Msg("No security warnings were detected for your installed models. Please note that this is a BEST EFFORT tool, and all issues may not be detected.")
-		} else {
-			log.Error().Err(err).Msg("! WARNING ! A known-vulnerable model is installed!")
-		}
-		return err
-	} else {
-		var errs error = nil
-		for _, uri := range hfscmd.ToScan {
-			log.Info().Str("uri", uri).Msg("scanning specific uri")
-			scanResults, err := downloader.HuggingFaceScan(uri)
-			if err != nil && !errors.Is(err, downloader.ErrNonHuggingFaceFile) {
-				log.Error().Err(err).Strs("clamAV", scanResults.ClamAVInfectedFiles).Strs("pickles", scanResults.DangerousPickles).Msg("! WARNING ! A known-vulnerable model is included in this repo!")
-				errs = errors.Join(errs, err)
-			}
-		}
-		if errs != nil {
-			return errs
-		}
-		log.Info().Msg("No security warnings were detected for your installed models. Please note that this is a BEST EFFORT tool, and all issues may not be detected.")
-		return nil
-	}
-}
--- a/core/cli/worker/worker_llamacpp.go
+++ b/core/cli/worker/worker_llamacpp.go
@@ -5,9 +5,8 @@ import (
 	"os"
 	"syscall"

-	cliContext "github.com/mudler/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/pkg/assets"
-	"github.com/mudler/LocalAI/pkg/library"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
+	"github.com/go-skynet/LocalAI/pkg/assets"
 	"github.com/rs/zerolog/log"
 )

@@ -28,18 +27,17 @@ func (r *LLamaCPP) Run(ctx *cliContext.Context) error {
 		return fmt.Errorf("usage: local-ai worker llama-cpp-rpc -- <llama-rpc-server-args>")
 	}

-	grpcProcess := assets.ResolvePath(
-		r.BackendAssetsPath,
-		"util",
-		"llama-cpp-rpc-server",
-	)
-
-	args := os.Args[4:]
-	args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
-
-	args = append([]string{grpcProcess}, args...)
 	return syscall.Exec(
-		grpcProcess,
-		args,
+		assets.ResolvePath(
+			r.BackendAssetsPath,
+			"util",
+			"llama-cpp-rpc-server",
+		),
+		append([]string{
+			assets.ResolvePath(
+				r.BackendAssetsPath,
+				"util",
+				"llama-cpp-rpc-server",
+			)}, os.Args[4:]...),
 		os.Environ())
 }
--- a/core/cli/worker/worker_nop2p.go
+++ b/core/cli/worker/worker_nop2p.go
@@ -6,7 +6,7 @@ package worker
 import (
 	"fmt"

-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
 )

 type P2P struct{}
--- a/core/cli/worker/worker_p2p.go
+++ b/core/cli/worker/worker_p2p.go
@@ -10,17 +10,16 @@ import (
 	"os/exec"
 	"time"

-	cliContext "github.com/mudler/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/pkg/assets"
-	"github.com/mudler/LocalAI/pkg/library"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
+	"github.com/go-skynet/LocalAI/core/p2p"
+	"github.com/go-skynet/LocalAI/pkg/assets"
 	"github.com/phayes/freeport"
 	"github.com/rs/zerolog/log"
 )

 type P2P struct {
 	WorkerFlags       `embed:""`
-	Token             string   `env:"LOCALAI_TOKEN,LOCALAI_P2P_TOKEN,TOKEN" help:"P2P token to use"`
+	Token             string   `env:"LOCALAI_TOKEN,TOKEN" help:"JSON list of galleries"`
 	NoRunner          bool     `env:"LOCALAI_NO_RUNNER,NO_RUNNER" help:"Do not start the llama-cpp-rpc-server"`
 	RunnerAddress     string   `env:"LOCALAI_RUNNER_ADDRESS,RUNNER_ADDRESS" help:"Address of the llama-cpp-rpc-server"`
 	RunnerPort        string   `env:"LOCALAI_RUNNER_PORT,RUNNER_PORT" help:"Port of the llama-cpp-rpc-server"`
@@ -59,7 +58,7 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
 			p = r.RunnerPort
 		}

-		err = p2p.ExposeService(context.Background(), address, p, r.Token, "")
+		err = p2p.BindLLamaCPPWorker(context.Background(), address, p, r.Token)
 		if err != nil {
 			return err
 		}
@@ -72,18 +71,13 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
 	go func() {
 		for {
 			log.Info().Msgf("Starting llama-cpp-rpc-server on '%s:%d'", address, port)
-
-			grpcProcess := assets.ResolvePath(
-				r.BackendAssetsPath,
-				"util",
-				"llama-cpp-rpc-server",
-			)
-
-			args := append([]string{"--host", address, "--port", fmt.Sprint(port)}, r.ExtraLLamaCPPArgs...)
-			args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
-
 			cmd := exec.Command(
-				grpcProcess, args...,
+				assets.ResolvePath(
+					r.BackendAssetsPath,
+					"util",
+					"llama-cpp-rpc-server",
+				),
+				append([]string{"--host", address, "--port", fmt.Sprint(port)}, r.ExtraLLamaCPPArgs...)...,
 			)

 			cmd.Env = os.Environ()
@@ -92,14 +86,14 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
 			cmd.Stdout = os.Stdout

 			if err := cmd.Start(); err != nil {
-				log.Error().Any("grpcProcess", grpcProcess).Any("args", args).Err(err).Msg("Failed to start llama-cpp-rpc-server")
+				log.Error().Err(err).Msg("Failed to start llama-cpp-rpc-server")
 			}

 			cmd.Wait()
 		}
 	}()

-	err = p2p.ExposeService(context.Background(), address, fmt.Sprint(port), r.Token, "")
+	err = p2p.BindLLamaCPPWorker(context.Background(), address, fmt.Sprint(port), r.Token)
 	if err != nil {
 		return err
 	}
--- a/core/config/application_config.go
+++ b/core/config/application_config.go
@@ -6,7 +6,8 @@ import (
 	"encoding/json"
 	"time"

-	"github.com/mudler/LocalAI/pkg/xsysinfo"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/xsysinfo"
 	"github.com/rs/zerolog/log"
 )

@@ -14,7 +15,6 @@ type ApplicationConfig struct {
 	Context                             context.Context
 	ConfigFile                          string
 	ModelPath                           string
-	LibPath                             string
 	UploadLimitMB, Threads, ContextSize int
 	DisableWebUI                        bool
 	F16                                 bool
@@ -31,13 +31,11 @@ type ApplicationConfig struct {
 	PreloadModelsFromPath               string
 	CORSAllowOrigins                    string
 	ApiKeys                             []string
-	EnforcePredownloadScans             bool
 	OpaqueErrors                        bool
-	P2PToken                            string

 	ModelLibraryURL string

-	Galleries []Gallery
+	Galleries []gallery.Gallery

 	BackendAssets     embed.FS
 	AssetsDestination string
@@ -97,24 +95,12 @@ func WithCsrf(b bool) AppOption {
 	}
 }

-func WithP2PToken(s string) AppOption {
-	return func(o *ApplicationConfig) {
-		o.P2PToken = s
-	}
-}
-
 func WithModelLibraryURL(url string) AppOption {
 	return func(o *ApplicationConfig) {
 		o.ModelLibraryURL = url
 	}
 }

-func WithLibPath(path string) AppOption {
-	return func(o *ApplicationConfig) {
-		o.LibPath = path
-	}
-}
-
 var EnableWatchDog = func(o *ApplicationConfig) {
 	o.WatchDog = true
 }
@@ -187,10 +173,10 @@ func WithBackendAssets(f embed.FS) AppOption {
 func WithStringGalleries(galls string) AppOption {
 	return func(o *ApplicationConfig) {
 		if galls == "" {
-			o.Galleries = []Gallery{}
+			o.Galleries = []gallery.Gallery{}
 			return
 		}
-		var galleries []Gallery
+		var galleries []gallery.Gallery
 		if err := json.Unmarshal([]byte(galls), &galleries); err != nil {
 			log.Error().Err(err).Msg("failed loading galleries")
 		}
@@ -198,7 +184,7 @@ func WithStringGalleries(galls string) AppOption {
 	}
 }

-func WithGalleries(galleries []Gallery) AppOption {
+func WithGalleries(galleries []gallery.Gallery) AppOption {
 	return func(o *ApplicationConfig) {
 		o.Galleries = append(o.Galleries, galleries...)
 	}
@@ -302,12 +288,6 @@ func WithApiKeys(apiKeys []string) AppOption {
 	}
 }

-func WithEnforcedPredownloadScans(enforced bool) AppOption {
-	return func(o *ApplicationConfig) {
-		o.EnforcePredownloadScans = enforced
-	}
-}
-
 func WithOpaqueErrors(opaque bool) AppOption {
 	return func(o *ApplicationConfig) {
 		o.OpaqueErrors = opaque
--- a/core/config/backend_config.go
+++ b/core/config/backend_config.go
@@ -5,10 +5,10 @@ import (
 	"regexp"
 	"strings"

-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/functions"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 )

 const (
@@ -390,6 +390,10 @@ func (c *BackendConfig) Validate() bool {
 		}
 	}

+	if c.Name == "" {
+		return false
+	}
+
 	if c.Backend != "" {
 		// a regex that checks that is a string name with no special characters, except '-' and '_'
 		re := regexp.MustCompile(`^[a-zA-Z0-9-_]+$`)
--- a/core/config/backend_config_loader.go
+++ b/core/config/backend_config_loader.go
@@ -11,9 +11,9 @@ import (
 	"sync"

 	"github.com/charmbracelet/glamour"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 	"gopkg.in/yaml.v3"
 )
--- a/core/config/backend_config_test.go
+++ b/core/config/backend_config_test.go
@@ -16,8 +16,7 @@ var _ = Describe("Test cases for config related functions", func() {
 			Expect(err).To(BeNil())
 			defer os.Remove(tmp.Name())
 			_, err = tmp.WriteString(
-				`backend: "../foo-bar"
-name: "foo"
+				`backend: "foo-bar"
 parameters:
  model: "foo-bar"`)
 			Expect(err).ToNot(HaveOccurred())
--- a/core/config/gallery.go
+++ b/core/config/gallery.go
@@ -1,6 +0,0 @@
-package config
-
-type Gallery struct {
-	URL  string `json:"url" yaml:"url"`
-	Name string `json:"name" yaml:"name"`
-}
--- a/core/dependencies_manager/manager.go
+++ b/core/dependencies_manager/manager.go
@@ -5,8 +5,8 @@ import (
 	"os"
 	"path/filepath"

-	"github.com/mudler/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"gopkg.in/yaml.v3"
 )

--- a/core/http/app.go
+++ b/core/http/app.go
@@ -6,16 +6,16 @@ import (
 	"net/http"
 	"strings"

-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"

-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/http/endpoints/openai"
-	"github.com/mudler/LocalAI/core/http/routes"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/openai"
+	"github.com/go-skynet/LocalAI/core/http/routes"

-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/model"

 	"github.com/gofiber/contrib/fiberzerolog"
 	"github.com/gofiber/fiber/v2"
--- a/core/http/app_test.go
+++ b/core/http/app_test.go
@@ -13,15 +13,15 @@ import (
 	"path/filepath"
 	"runtime"

-	"github.com/mudler/LocalAI/core/config"
-	. "github.com/mudler/LocalAI/core/http"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/startup"
+	"github.com/go-skynet/LocalAI/core/config"
+	. "github.com/go-skynet/LocalAI/core/http"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/startup"

+	"github.com/go-skynet/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/model"
 	. "github.com/onsi/ginkgo/v2"
 	. "github.com/onsi/gomega"
 	"gopkg.in/yaml.v3"
@@ -74,7 +74,7 @@ func getModelStatus(url string) (response map[string]interface{}) {

 func getModels(url string) (response []gallery.GalleryModel) {
 	// TODO: No tests currently seem to exercise file:// urls. Fix?
-	downloader.DownloadAndUnmarshal(url, "", func(url string, i []byte) error {
+	downloader.GetURI(url, "", func(url string, i []byte) error {
 		// Unmarshal YAML data into a struct
 		return json.Unmarshal(i, &response)
 	})
@@ -247,7 +247,7 @@ var _ = Describe("API test", func() {
 			err = os.WriteFile(filepath.Join(modelDir, "gallery_simple.yaml"), out, 0600)
 			Expect(err).ToNot(HaveOccurred())

-			galleries := []config.Gallery{
+			galleries := []gallery.Gallery{
 				{
 					Name: "test",
 					URL:  "file://" + filepath.Join(modelDir, "gallery_simple.yaml"),
@@ -603,7 +603,7 @@ var _ = Describe("API test", func() {

 			c, cancel = context.WithCancel(context.Background())

-			galleries := []config.Gallery{
+			galleries := []gallery.Gallery{
 				{
 					Name: "model-gallery",
 					URL:  "https://raw.githubusercontent.com/go-skynet/model-gallery/main/index.yaml",
--- a/core/http/ctx/fiber.go
+++ b/core/http/ctx/fiber.go
@@ -4,10 +4,8 @@ import (
 	"fmt"
 	"strings"

+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )

@@ -15,7 +13,7 @@ import (
 // If no model is specified, it will take the first available
 // Takes a model string as input which should be the one received from the user request.
 // It returns the model name resolved from the context and an error if any.
-func ModelFromContext(ctx *fiber.Ctx, cl *config.BackendConfigLoader, loader *model.ModelLoader, modelInput string, firstModel bool) (string, error) {
+func ModelFromContext(ctx *fiber.Ctx, loader *model.ModelLoader, modelInput string, firstModel bool) (string, error) {
 	if ctx.Params("model") != "" {
 		modelInput = ctx.Params("model")
 	}
@@ -26,7 +24,7 @@ func ModelFromContext(ctx *fiber.Ctx, cl *config.BackendConfigLoader, loader *mo

 	// If no model was specified, take the first available
 	if modelInput == "" && !bearerExists && firstModel {
-		models, _ := services.ListModels(cl, loader, "", true)
+		models, _ := loader.ListModels()
 		if len(models) > 0 {
 			modelInput = models[0]
 			log.Debug().Msgf("No model specified, using: %s", modelInput)
--- a/core/http/elements/gallery.go
+++ b/core/http/elements/gallery.go
@@ -6,24 +6,15 @@ import (

 	"github.com/chasefleming/elem-go"
 	"github.com/chasefleming/elem-go/attrs"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/xsync"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/xsync"
 )

 const (
 	noImage = "https://upload.wikimedia.org/wikipedia/commons/6/65/No-Image-Placeholder.svg"
 )

-func renderElements(n []elem.Node) string {
-	render := ""
-	for _, r := range n {
-		render += r.Render()
-	}
-	return render
-}
-
 func DoneProgress(galleryID, text string, showDelete bool) string {
 	var modelName = galleryID
 	// Split by @ and grab the name
@@ -81,135 +72,6 @@ func ProgressBar(progress string) string {
 	).Render()
 }

-func P2PNodeStats(nodes []p2p.NodeData) string {
-	/*
-	   <div class="bg-gray-800 p-6 rounded-lg shadow-lg text-left">
-	                       <p class="text-xl font-semibold text-gray-200">Total Workers Detected: {{ len .Nodes }}</p>
-	                       {{ $online := 0 }}
-	                       {{ range .Nodes }}
-	                           {{ if .IsOnline }}
-	                               {{ $online = add $online 1 }}
-	                           {{ end }}
-	                       {{ end }}
-	                       <p class="text-xl font-semibold text-gray-200">Total Online Workers: {{$online}}</p>
-	                   </div>
-	*/
-
-	online := 0
-	for _, n := range nodes {
-		if n.IsOnline() {
-			online++
-		}
-	}
-
-	class := "text-green-500"
-	if online == 0 {
-		class = "text-red-500"
-	}
-	/*
-	   <i class="fas fa-circle animate-pulse text-green-500 ml-2 mr-1"></i>
-	*/
-	circle := elem.I(attrs.Props{
-		"class": "fas fa-circle animate-pulse " + class + " ml-2 mr-1",
-	})
-	nodesElements := []elem.Node{
-		elem.Span(
-			attrs.Props{
-				"class": class,
-			},
-			circle,
-			elem.Text(fmt.Sprintf("%d", online)),
-		),
-		elem.Span(
-			attrs.Props{
-				"class": "text-gray-200",
-			},
-			elem.Text(fmt.Sprintf("/%d", len(nodes))),
-		),
-	}
-
-	return renderElements(nodesElements)
-}
-
-func P2PNodeBoxes(nodes []p2p.NodeData) string {
-	/*
-			<div class="bg-gray-800 p-4 rounded-lg shadow-lg text-left">
-			<div class="flex items-center mb-2">
-				<i class="fas fa-desktop text-gray-400 mr-2"></i>
-				<span class="text-gray-200 font-semibold">{{.ID}}</span>
-			</div>
-			<p class="text-sm text-gray-400 mt-2 flex items-center">
-				Status:
-				<i class="fas fa-circle {{ if .IsOnline }}text-green-500{{ else }}text-red-500{{ end }} ml-2 mr-1"></i>
-				<span class="{{ if .IsOnline }}text-green-400{{ else }}text-red-400{{ end }}">
-					{{ if .IsOnline }}Online{{ else }}Offline{{ end }}
-				</span>
-			</p>
-		</div>
-	*/
-
-	nodesElements := []elem.Node{}
-
-	for _, n := range nodes {
-
-		nodesElements = append(nodesElements,
-			elem.Div(
-				attrs.Props{
-					"class": "bg-gray-700 p-6 rounded-lg shadow-lg text-left",
-				},
-				elem.P(
-					attrs.Props{
-						"class": "text-sm text-gray-400 mt-2 flex",
-					},
-					elem.I(
-						attrs.Props{
-							"class": "fas fa-desktop text-gray-400 mr-2",
-						},
-					),
-					elem.Text("Name: "),
-					elem.Span(
-						attrs.Props{
-							"class": "text-gray-200 font-semibold ml-2 mr-1",
-						},
-						elem.Text(n.ID),
-					),
-					elem.Text("Status: "),
-					elem.If(
-						n.IsOnline(),
-						elem.I(
-							attrs.Props{
-								"class": "fas fa-circle animate-pulse text-green-500 ml-2 mr-1",
-							},
-						),
-						elem.I(
-							attrs.Props{
-								"class": "fas fa-circle animate-pulse text-red-500 ml-2 mr-1",
-							},
-						),
-					),
-					elem.If(
-						n.IsOnline(),
-						elem.Span(
-							attrs.Props{
-								"class": "text-green-400",
-							},
-
-							elem.Text("Online"),
-						),
-						elem.Span(
-							attrs.Props{
-								"class": "text-red-400",
-							},
-							elem.Text("Offline"),
-						),
-					),
-				),
-			))
-	}
-
-	return renderElements(nodesElements)
-}
-
 func StartProgressBar(uid, progress, text string) string {
 	if progress == "" {
 		progress = "0"
--- a/core/http/endpoints/elevenlabs/tts.go
+++ b/core/http/endpoints/elevenlabs/tts.go
@@ -1,13 +1,13 @@
 package elevenlabs

 import (
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
+	"github.com/go-skynet/LocalAI/pkg/model"

+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
 	"github.com/rs/zerolog/log"
 )

@@ -28,7 +28,7 @@ func TTSEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfi
 			return err
 		}

-		modelFile, err := fiberContext.ModelFromContext(c, cl, ml, input.ModelID, false)
+		modelFile, err := fiberContext.ModelFromContext(c, ml, input.ModelID, false)
 		if err != nil {
 			modelFile = input.ModelID
 			log.Warn().Msgf("Model not found in context: %s", input.ModelID)
--- a/core/http/endpoints/jina/rerank.go
+++ b/core/http/endpoints/jina/rerank.go
@@ -1,14 +1,14 @@
 package jina

 import (
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"

+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )

@@ -28,7 +28,7 @@ func JINARerankEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, a
 			return err
 		}

-		modelFile, err := fiberContext.ModelFromContext(c, cl, ml, input.Model, false)
+		modelFile, err := fiberContext.ModelFromContext(c, ml, input.Model, false)
 		if err != nil {
 			modelFile = input.Model
 			log.Warn().Msgf("Model not found in context: %s", input.Model)
--- a/core/http/endpoints/localai/backend_monitor.go
+++ b/core/http/endpoints/localai/backend_monitor.go
@@ -1,9 +1,9 @@
 package localai

 import (
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/services"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/services"
 )

 func BackendMonitorEndpoint(bm *services.BackendMonitorService) func(c *fiber.Ctx) error {
--- a/core/http/endpoints/localai/gallery.go
+++ b/core/http/endpoints/localai/gallery.go
@@ -5,16 +5,15 @@ import (
 	"fmt"
 	"slices"

+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/core/services"
 	"github.com/rs/zerolog/log"
 )

 type ModelGalleryEndpointService struct {
-	galleries      []config.Gallery
+	galleries      []gallery.Gallery
 	modelPath      string
 	galleryApplier *services.GalleryService
 }
@@ -25,7 +24,7 @@ type GalleryModel struct {
 	gallery.GalleryModel
 }

-func CreateModelGalleryEndpointService(galleries []config.Gallery, modelPath string, galleryApplier *services.GalleryService) ModelGalleryEndpointService {
+func CreateModelGalleryEndpointService(galleries []gallery.Gallery, modelPath string, galleryApplier *services.GalleryService) ModelGalleryEndpointService {
 	return ModelGalleryEndpointService{
 		galleries:      galleries,
 		modelPath:      modelPath,
@@ -130,12 +129,12 @@ func (mgs *ModelGalleryEndpointService) ListModelGalleriesEndpoint() func(c *fib

 func (mgs *ModelGalleryEndpointService) AddModelGalleryEndpoint() func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		input := new(config.Gallery)
+		input := new(gallery.Gallery)
 		// Get input data from the request body
 		if err := c.BodyParser(input); err != nil {
 			return err
 		}
-		if slices.ContainsFunc(mgs.galleries, func(gallery config.Gallery) bool {
+		if slices.ContainsFunc(mgs.galleries, func(gallery gallery.Gallery) bool {
 			return gallery.Name == input.Name
 		}) {
 			return fmt.Errorf("%s already exists", input.Name)
@@ -152,17 +151,17 @@ func (mgs *ModelGalleryEndpointService) AddModelGalleryEndpoint() func(c *fiber.

 func (mgs *ModelGalleryEndpointService) RemoveModelGalleryEndpoint() func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		input := new(config.Gallery)
+		input := new(gallery.Gallery)
 		// Get input data from the request body
 		if err := c.BodyParser(input); err != nil {
 			return err
 		}
-		if !slices.ContainsFunc(mgs.galleries, func(gallery config.Gallery) bool {
+		if !slices.ContainsFunc(mgs.galleries, func(gallery gallery.Gallery) bool {
 			return gallery.Name == input.Name
 		}) {
 			return fmt.Errorf("%s is not currently registered", input.Name)
 		}
-		mgs.galleries = slices.DeleteFunc(mgs.galleries, func(gallery config.Gallery) bool {
+		mgs.galleries = slices.DeleteFunc(mgs.galleries, func(gallery gallery.Gallery) bool {
 			return gallery.Name == input.Name
 		})
 		return c.Send(nil)
--- a/core/http/endpoints/localai/metrics.go
+++ b/core/http/endpoints/localai/metrics.go
@@ -3,9 +3,9 @@ package localai
 import (
 	"time"

+	"github.com/go-skynet/LocalAI/core/services"
 	"github.com/gofiber/fiber/v2"
 	"github.com/gofiber/fiber/v2/middleware/adaptor"
-	"github.com/mudler/LocalAI/core/services"
 	"github.com/prometheus/client_golang/prometheus/promhttp"
 )

--- a/core/http/endpoints/localai/stores.go
+++ b/core/http/endpoints/localai/stores.go
@@ -1,12 +1,12 @@
 package localai

 import (
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/store"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/store"
 )

 func StoresSetEndpoint(sl *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
--- a/core/http/endpoints/localai/tts.go
+++ b/core/http/endpoints/localai/tts.go
@@ -1,13 +1,13 @@
 package localai

 import (
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
+	"github.com/go-skynet/LocalAI/pkg/model"

+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
 	"github.com/rs/zerolog/log"
 )

@@ -29,7 +29,7 @@ func TTSEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfi
 			return err
 		}

-		modelFile, err := fiberContext.ModelFromContext(c, cl, ml, input.Model, false)
+		modelFile, err := fiberContext.ModelFromContext(c, ml, input.Model, false)
 		if err != nil {
 			modelFile = input.Model
 			log.Warn().Msgf("Model not found in context: %s", input.Model)
--- a/core/http/endpoints/localai/welcome.go
+++ b/core/http/endpoints/localai/welcome.go
@@ -1,19 +1,17 @@
 package localai

 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/internal"
-	"github.com/mudler/LocalAI/pkg/model"
 )

 func WelcomeEndpoint(appConfig *config.ApplicationConfig,
 	cl *config.BackendConfigLoader, ml *model.ModelLoader, modelStatus func() (map[string]string, map[string]string)) func(*fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		models, _ := services.ListModels(cl, ml, "", true)
+		models, _ := ml.ListModels()
 		backendConfigs := cl.GetAllBackendConfigs()

 		galleryConfigs := map[string]*gallery.Config{}
@@ -35,7 +33,6 @@ func WelcomeEndpoint(appConfig *config.ApplicationConfig,
 			"Models":            models,
 			"ModelsConfig":      backendConfigs,
 			"GalleryConfig":     galleryConfigs,
-			"IsP2PEnabled":      p2p.IsP2PEnabled(),
 			"ApplicationConfig": appConfig,
 			"ProcessingModels":  processingModels,
 			"TaskTypes":         taskTypes,
--- a/core/http/endpoints/openai/assistant.go
+++ b/core/http/endpoints/openai/assistant.go
@@ -9,11 +9,10 @@ import (
 	"sync/atomic"
 	"time"

+	"github.com/go-skynet/LocalAI/core/config"
+	model "github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/services"
-	model "github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 )

@@ -80,7 +79,7 @@ func CreateAssistantEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoad
 			return c.Status(fiber.StatusBadRequest).JSON(fiber.Map{"error": "Cannot parse JSON"})
 		}

-		if !modelExists(cl, ml, request.Model) {
+		if !modelExists(ml, request.Model) {
 			log.Warn().Msgf("Model: %s was not found in list of models.", request.Model)
 			return c.Status(fiber.StatusBadRequest).SendString("Model " + request.Model + " not found")
 		}
@@ -214,9 +213,9 @@ func filterAssistantsAfterID(assistants []Assistant, id string) []Assistant {
 	return filteredAssistants
 }

-func modelExists(cl *config.BackendConfigLoader, ml *model.ModelLoader, modelName string) (found bool) {
+func modelExists(ml *model.ModelLoader, modelName string) (found bool) {
 	found = false
-	models, err := services.ListModels(cl, ml, "", true)
+	models, err := ml.ListModels()
 	if err != nil {
 		return
 	}
@@ -340,7 +339,7 @@ func CreateAssistantFileEndpoint(cl *config.BackendConfigLoader, ml *model.Model
 			}
 		}

-		return c.Status(fiber.StatusNotFound).SendString(fmt.Sprintf("Unable to find %q", assistantID))
+		return c.Status(fiber.StatusNotFound).SendString(fmt.Sprintf("Unable to find "))
 	}
 }

--- a/core/http/endpoints/openai/assistant_test.go
+++ b/core/http/endpoints/openai/assistant_test.go
@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"io/ioutil"
 	"net/http"
 	"net/http/httptest"
 	"os"
@@ -12,9 +13,9 @@ import (
 	"testing"
 	"time"

+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/stretchr/testify/assert"
 )

@@ -182,7 +183,7 @@ func TestAssistantEndpoints(t *testing.T) {
 				assert.NoError(t, err)
 				assert.Equal(t, tt.expectedStatus, response.StatusCode)
 				if tt.expectedStatus != fiber.StatusOK {
-					all, _ := io.ReadAll(response.Body)
+					all, _ := ioutil.ReadAll(response.Body)
 					assert.Equal(t, tt.expectedStringResult, string(all))
 				} else {
 					var result []Assistant
@@ -278,7 +279,6 @@ func TestAssistantEndpoints(t *testing.T) {
 		assert.NoError(t, err)
 		var getAssistant Assistant
 		err = json.NewDecoder(modifyResponse.Body).Decode(&getAssistant)
-		assert.NoError(t, err)

 		t.Cleanup(cleanupAllAssistants(t, app, []string{getAssistant.ID}))

@@ -391,10 +391,7 @@ func createAssistantFile(app *fiber.App, afr AssistantFileRequest, assistantId s
 	}

 	var assistantFile AssistantFile
-	all, err := io.ReadAll(resp.Body)
-	if err != nil {
-		return AssistantFile{}, resp, err
-	}
+	all, err := ioutil.ReadAll(resp.Body)
 	err = json.NewDecoder(strings.NewReader(string(all))).Decode(&assistantFile)
 	if err != nil {
 		return AssistantFile{}, resp, err
@@ -425,7 +422,8 @@ func createAssistant(app *fiber.App, ar AssistantRequest) (Assistant, *http.Resp

 	var resultAssistant Assistant
 	err = json.NewDecoder(strings.NewReader(string(bodyString))).Decode(&resultAssistant)
-	return resultAssistant, resp, err
+
+	return resultAssistant, resp, nil
 }

 func cleanupAllAssistants(t *testing.T, app *fiber.App, ids []string) func() {
--- a/core/http/endpoints/openai/chat.go
+++ b/core/http/endpoints/openai/chat.go
@@ -8,13 +8,13 @@ import (
 	"strings"
 	"time"

+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/functions"
-	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 	"github.com/valyala/fasthttp"
 )
@@ -159,7 +159,7 @@ func ChatEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, startup
 	}

 	return func(c *fiber.Ctx) error {
-		modelFile, input, err := readRequest(c, cl, ml, startupOptions, true)
+		modelFile, input, err := readRequest(c, ml, startupOptions, true)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
--- a/core/http/endpoints/openai/completion.go
+++ b/core/http/endpoints/openai/completion.go
@@ -8,14 +8,14 @@ import (
 	"fmt"
 	"time"

-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"

+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/functions"
-	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 	"github.com/valyala/fasthttp"
 )
@@ -57,7 +57,7 @@ func CompletionEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, a
 	}

 	return func(c *fiber.Ctx) error {
-		modelFile, input, err := readRequest(c, cl, ml, appConfig, true)
+		modelFile, input, err := readRequest(c, ml, appConfig, true)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
--- a/core/http/endpoints/openai/edit.go
+++ b/core/http/endpoints/openai/edit.go
@@ -5,20 +5,20 @@ import (
 	"fmt"
 	"time"

-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"

+	"github.com/go-skynet/LocalAI/core/schema"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/schema"
-	model "github.com/mudler/LocalAI/pkg/model"

 	"github.com/rs/zerolog/log"
 )

 func EditEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		modelFile, input, err := readRequest(c, cl, ml, appConfig, true)
+		modelFile, input, err := readRequest(c, ml, appConfig, true)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
--- a/core/http/endpoints/openai/embeddings.go
+++ b/core/http/endpoints/openai/embeddings.go
@@ -5,12 +5,12 @@ import (
 	"fmt"
 	"time"

-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/pkg/model"

+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/schema"

 	"github.com/gofiber/fiber/v2"
 	"github.com/rs/zerolog/log"
@@ -23,7 +23,7 @@ import (
 // @Router /v1/embeddings [post]
 func EmbeddingsEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		model, input, err := readRequest(c, cl, ml, appConfig, true)
+		model, input, err := readRequest(c, ml, appConfig, true)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
--- a/core/http/endpoints/openai/files.go
+++ b/core/http/endpoints/openai/files.go
@@ -8,10 +8,10 @@ import (
 	"sync/atomic"
 	"time"

-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"

+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/pkg/utils"
 )

 var UploadedFiles []File
@@ -123,10 +123,7 @@ func getFileFromRequest(c *fiber.Ctx) (*File, error) {
 	return nil, fmt.Errorf("unable to find file id %s", id)
 }

-// GetFilesEndpoint is the OpenAI API endpoint to get files https://platform.openai.com/docs/api-reference/files/retrieve
-// @Summary Returns information about a specific file.
-// @Success 200 {object} File "Response"
-// @Router /v1/files/{file_id} [get]
+// GetFilesEndpoint https://platform.openai.com/docs/api-reference/files/retrieve
 func GetFilesEndpoint(cm *config.BackendConfigLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
 		file, err := getFileFromRequest(c)
@@ -138,17 +135,13 @@ func GetFilesEndpoint(cm *config.BackendConfigLoader, appConfig *config.Applicat
 	}
 }

-type DeleteStatus struct {
-	Id      string
-	Object  string
-	Deleted bool
-}
-
-// DeleteFilesEndpoint is the OpenAI API endpoint to delete files https://platform.openai.com/docs/api-reference/files/delete
-// @Summary Delete a file.
-// @Success 200 {object} DeleteStatus "Response"
-// @Router /v1/files/{file_id} [delete]
+// DeleteFilesEndpoint https://platform.openai.com/docs/api-reference/files/delete
 func DeleteFilesEndpoint(cm *config.BackendConfigLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
+	type DeleteStatus struct {
+		Id      string
+		Object  string
+		Deleted bool
+	}

 	return func(c *fiber.Ctx) error {
 		file, err := getFileFromRequest(c)
@@ -181,11 +174,7 @@ func DeleteFilesEndpoint(cm *config.BackendConfigLoader, appConfig *config.Appli
 	}
 }

-// GetFilesContentsEndpoint is the OpenAI API endpoint to get files content https://platform.openai.com/docs/api-reference/files/retrieve-contents
-// @Summary Returns information about a specific file.
-// @Success	200		{string}	binary				"file"
-// @Router /v1/files/{file_id}/content [get]
-// GetFilesContentsEndpoint
+// GetFilesContentsEndpoint https://platform.openai.com/docs/api-reference/files/retrieve-contents
 func GetFilesContentsEndpoint(cm *config.BackendConfigLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
 		file, err := getFileFromRequest(c)
--- a/core/http/endpoints/openai/files_test.go
+++ b/core/http/endpoints/openai/files_test.go
@@ -13,10 +13,10 @@ import (

 	"github.com/rs/zerolog/log"

-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"

+	utils2 "github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/gofiber/fiber/v2"
-	utils2 "github.com/mudler/LocalAI/pkg/utils"
 	"github.com/stretchr/testify/assert"

 	"testing"
--- a/core/http/endpoints/openai/image.go
+++ b/core/http/endpoints/openai/image.go
@@ -13,14 +13,14 @@ import (
 	"strings"
 	"time"

+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"

-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"

+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )

@@ -66,7 +66,7 @@ func downloadFile(url string) (string, error) {
 // @Router /v1/images/generations [post]
 func ImageEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		m, input, err := readRequest(c, cl, ml, appConfig, false)
+		m, input, err := readRequest(c, ml, appConfig, false)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
--- a/core/http/endpoints/openai/inference.go
+++ b/core/http/endpoints/openai/inference.go
@@ -1,11 +1,11 @@
 package openai

 import (
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"

-	"github.com/mudler/LocalAI/core/schema"
-	model "github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/schema"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )

 func ComputeChoices(
--- a/core/http/endpoints/openai/list.go
+++ b/core/http/endpoints/openai/list.go
@@ -1,18 +1,12 @@
 package openai

 import (
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/services"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/services"
-	model "github.com/mudler/LocalAI/pkg/model"
 )

-// ListModelsEndpoint is the OpenAI Models API endpoint https://platform.openai.com/docs/api-reference/models
-// @Summary List and describe the various models available in the API.
-// @Success 200 {object} schema.ModelsDataResponse "Response"
-// @Router /v1/models [get]
-func ListModelsEndpoint(bcl *config.BackendConfigLoader, ml *model.ModelLoader) func(ctx *fiber.Ctx) error {
+func ListModelsEndpoint(lms *services.ListModelsService) func(ctx *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
 		// If blank, no filter is applied.
 		filter := c.Query("filter")
@@ -20,30 +14,16 @@ func ListModelsEndpoint(bcl *config.BackendConfigLoader, ml *model.ModelLoader)
 		// By default, exclude any loose files that are already referenced by a configuration file.
 		excludeConfigured := c.QueryBool("excludeConfigured", true)

-		dataModels, err := modelList(bcl, ml, filter, excludeConfigured)
+		dataModels, err := lms.ListModels(filter, excludeConfigured)
 		if err != nil {
 			return err
 		}
-		return c.JSON(schema.ModelsDataResponse{
+		return c.JSON(struct {
+			Object string               `json:"object"`
+			Data   []schema.OpenAIModel `json:"data"`
+		}{
 			Object: "list",
 			Data:   dataModels,
 		})
 	}
 }
-
-func modelList(bcl *config.BackendConfigLoader, ml *model.ModelLoader, filter string, excludeConfigured bool) ([]schema.OpenAIModel, error) {
-
-	models, err := services.ListModels(bcl, ml, filter, excludeConfigured)
-	if err != nil {
-		return nil, err
-	}
-
-	dataModels := []schema.OpenAIModel{}
-
-	// Then iterate through the loose files:
-	for _, m := range models {
-		dataModels = append(dataModels, schema.OpenAIModel{ID: m, Object: "model"})
-	}
-
-	return dataModels, nil
-}
--- a/core/http/endpoints/openai/request.go
+++ b/core/http/endpoints/openai/request.go
@@ -2,20 +2,23 @@ package openai

 import (
 	"context"
+	"encoding/base64"
 	"encoding/json"
 	"fmt"
+	"io"
+	"net/http"
+	"strings"

+	"github.com/go-skynet/LocalAI/core/config"
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/functions"
-	"github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 )

-func readRequest(c *fiber.Ctx, cl *config.BackendConfigLoader, ml *model.ModelLoader, o *config.ApplicationConfig, firstModel bool) (string, *schema.OpenAIRequest, error) {
+func readRequest(c *fiber.Ctx, ml *model.ModelLoader, o *config.ApplicationConfig, firstModel bool) (string, *schema.OpenAIRequest, error) {
 	input := new(schema.OpenAIRequest)

 	// Get input data from the request body
@@ -31,11 +34,46 @@ func readRequest(c *fiber.Ctx, cl *config.BackendConfigLoader, ml *model.ModelLo

 	log.Debug().Msgf("Request received: %s", string(received))

-	modelFile, err := fiberContext.ModelFromContext(c, cl, ml, input.Model, firstModel)
+	modelFile, err := fiberContext.ModelFromContext(c, ml, input.Model, firstModel)

 	return modelFile, input, err
 }

+// this function check if the string is an URL, if it's an URL downloads the image in memory
+// encodes it in base64 and returns the base64 string
+func getBase64Image(s string) (string, error) {
+	if strings.HasPrefix(s, "http") {
+		// download the image
+		resp, err := http.Get(s)
+		if err != nil {
+			return "", err
+		}
+		defer resp.Body.Close()
+
+		// read the image data into memory
+		data, err := io.ReadAll(resp.Body)
+		if err != nil {
+			return "", err
+		}
+
+		// encode the image data in base64
+		encoded := base64.StdEncoding.EncodeToString(data)
+
+		// return the base64 string
+		return encoded, nil
+	}
+
+	// if the string instead is prefixed with "data:image/...;base64,", drop it
+	dropPrefix := []string{"data:image/jpeg;base64,", "data:image/png;base64,"}
+	for _, prefix := range dropPrefix {
+		if strings.HasPrefix(s, prefix) {
+			return strings.ReplaceAll(s, prefix, ""), nil
+		}
+	}
+
+	return "", fmt.Errorf("not valid string")
+}
+
 func updateRequestConfig(config *config.BackendConfig, input *schema.OpenAIRequest) {
 	if input.Echo {
 		config.Echo = input.Echo
@@ -149,7 +187,7 @@ func updateRequestConfig(config *config.BackendConfig, input *schema.OpenAIReque
 					input.Messages[i].StringContent = pp.Text
 				} else if pp.Type == "image_url" {
 					// Detect if pp.ImageURL is an URL, if it is download the image and encode it in base64:
-					base64, err := utils.GetImageURLAsBase64(pp.ImageURL.URL)
+					base64, err := getBase64Image(pp.ImageURL.URL)
 					if err == nil {
 						input.Messages[i].StringImages = append(input.Messages[i].StringImages, base64) // TODO: make sure that we only return base64 stuff
 						// set a placeholder for each image
@@ -257,9 +295,5 @@ func mergeRequestWithConfig(modelFile string, input *schema.OpenAIRequest, cm *c
 	// Set the parameters for the language model prediction
 	updateRequestConfig(cfg, input)

-	if !cfg.Validate() {
-		return nil, nil, fmt.Errorf("failed to validate config")
-	}
-
 	return cfg, input, err
 }
--- a/core/http/endpoints/openai/transcription.go
+++ b/core/http/endpoints/openai/transcription.go
@@ -8,9 +8,9 @@ import (
 	"path"
 	"path/filepath"

-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	model "github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	model "github.com/go-skynet/LocalAI/pkg/model"

 	"github.com/gofiber/fiber/v2"
 	"github.com/rs/zerolog/log"
@@ -25,14 +25,14 @@ import (
 // @Router /v1/audio/transcriptions [post]
 func TranscriptEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		m, input, err := readRequest(c, cl, ml, appConfig, false)
+		m, input, err := readRequest(c, ml, appConfig, false)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}

 		config, input, err := mergeRequestWithConfig(m, input, cl, ml, appConfig.Debug, appConfig.Threads, appConfig.ContextSize, appConfig.F16)
 		if err != nil {
-			return fmt.Errorf("failed reading parameters from request: %w", err)
+			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
 		// retrieve the file data from the request
 		file, err := c.FormFile("file")
@@ -65,7 +65,7 @@ func TranscriptEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, a

 		log.Debug().Msgf("Audio file copied to: %+v", dst)

-		tr, err := backend.ModelTranscription(dst, input.Language, input.Translate, ml, *config, appConfig)
+		tr, err := backend.ModelTranscription(dst, input.Language, ml, *config, appConfig)
 		if err != nil {
 			return err
 		}
--- a/core/http/render.go
+++ b/core/http/render.go
@@ -7,10 +7,10 @@ import (
 	"net/http"

 	"github.com/Masterminds/sprig/v3"
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/gofiber/fiber/v2"
 	fiberhtml "github.com/gofiber/template/html/v2"
 	"github.com/microcosm-cc/bluemonday"
-	"github.com/mudler/LocalAI/core/schema"
 	"github.com/russross/blackfriday"
 )

@@ -21,13 +21,14 @@ func notFoundHandler(c *fiber.Ctx) error {
 	// Check if the request accepts JSON
 	if string(c.Context().Request.Header.ContentType()) == "application/json" || len(c.Accepts("html")) == 0 {
 		// The client expects a JSON response
-		return c.Status(fiber.StatusNotFound).JSON(schema.ErrorResponse{
+		c.Status(fiber.StatusNotFound).JSON(schema.ErrorResponse{
 			Error: &schema.APIError{Message: "Resource not found", Code: fiber.StatusNotFound},
 		})
 	} else {
 		// The client expects an HTML response
-		return c.Status(fiber.StatusNotFound).Render("views/404", fiber.Map{})
+		c.Status(fiber.StatusNotFound).Render("views/404", fiber.Map{})
 	}
+	return nil
 }

 func renderEngine() *fiberhtml.Engine {
--- a/core/http/routes/elevenlabs.go
+++ b/core/http/routes/elevenlabs.go
@@ -1,10 +1,10 @@
 package routes

 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/elevenlabs"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/elevenlabs"
-	"github.com/mudler/LocalAI/pkg/model"
 )

 func RegisterElevenLabsRoutes(app *fiber.App,
--- a/core/http/routes/jina.go
+++ b/core/http/routes/jina.go
@@ -1,11 +1,11 @@
 package routes

 import (
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/jina"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/jina"

+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/pkg/model"
 )

 func RegisterJINARoutes(app *fiber.App,
--- a/core/http/routes/localai.go
+++ b/core/http/routes/localai.go
@@ -1,14 +1,13 @@
 package routes

 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/gofiber/swagger"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/internal"
-	"github.com/mudler/LocalAI/pkg/model"
 )

 func RegisterLocalAIRoutes(app *fiber.App,
@@ -57,20 +56,6 @@ func RegisterLocalAIRoutes(app *fiber.App,
 	app.Get("/backend/monitor", auth, localai.BackendMonitorEndpoint(backendMonitorService))
 	app.Post("/backend/shutdown", auth, localai.BackendShutdownEndpoint(backendMonitorService))

-	// p2p
-	if p2p.IsP2PEnabled() {
-		app.Get("/api/p2p", auth, func(c *fiber.Ctx) error {
-			// Render index
-			return c.JSON(map[string]interface{}{
-				"Nodes":          p2p.GetAvailableNodes(""),
-				"FederatedNodes": p2p.GetAvailableNodes(p2p.FederatedID),
-			})
-		})
-		app.Get("/api/p2p/token", auth, func(c *fiber.Ctx) error {
-			return c.Send([]byte(appConfig.P2PToken))
-		})
-	}
-
 	app.Get("/version", auth, func(c *fiber.Ctx) error {
 		return c.JSON(struct {
 			Version string `json:"version"`
--- a/core/http/routes/openai.go
+++ b/core/http/routes/openai.go
@@ -1,11 +1,12 @@
 package routes

 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/openai"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/http/endpoints/openai"
-	"github.com/mudler/LocalAI/pkg/model"
 )

 func RegisterOpenAIRoutes(app *fiber.App,
@@ -80,7 +81,8 @@ func RegisterOpenAIRoutes(app *fiber.App,
 		app.Static("/generated-audio", appConfig.AudioDir)
 	}

-	// List models
-	app.Get("/v1/models", auth, openai.ListModelsEndpoint(cl, ml))
-	app.Get("/models", auth, openai.ListModelsEndpoint(cl, ml))
+	// models
+	tmpLMS := services.NewListModelsService(ml, cl, appConfig) // TODO: once createApplication() is fully in use, reference the central instance.
+	app.Get("/v1/models", auth, openai.ListModelsEndpoint(tmpLMS))
+	app.Get("/models", auth, openai.ListModelsEndpoint(tmpLMS))
 }
--- a/core/http/routes/ui.go
+++ b/core/http/routes/ui.go
@@ -6,15 +6,14 @@ import (
 	"sort"
 	"strings"

-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/core/http/elements"
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/internal"
-	"github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/xsync"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/elements"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/xsync"
 	"github.com/rs/zerolog/log"

 	"github.com/gofiber/fiber/v2"
@@ -53,37 +52,6 @@ func RegisterUIRoutes(app *fiber.App,

 	app.Get("/", auth, localai.WelcomeEndpoint(appConfig, cl, ml, modelStatus))

-	if p2p.IsP2PEnabled() {
-		app.Get("/p2p", auth, func(c *fiber.Ctx) error {
-			summary := fiber.Map{
-				"Title":   "LocalAI - P2P dashboard",
-				"Version": internal.PrintableVersion(),
-				//"Nodes":          p2p.GetAvailableNodes(""),
-				//"FederatedNodes": p2p.GetAvailableNodes(p2p.FederatedID),
-				"IsP2PEnabled": p2p.IsP2PEnabled(),
-				"P2PToken":     appConfig.P2PToken,
-			}
-
-			// Render index
-			return c.Render("views/p2p", summary)
-		})
-
-		/* show nodes live! */
-		app.Get("/p2p/ui/workers", auth, func(c *fiber.Ctx) error {
-			return c.SendString(elements.P2PNodeBoxes(p2p.GetAvailableNodes("")))
-		})
-		app.Get("/p2p/ui/workers-federation", auth, func(c *fiber.Ctx) error {
-			return c.SendString(elements.P2PNodeBoxes(p2p.GetAvailableNodes(p2p.FederatedID)))
-		})
-
-		app.Get("/p2p/ui/workers-stats", auth, func(c *fiber.Ctx) error {
-			return c.SendString(elements.P2PNodeStats(p2p.GetAvailableNodes("")))
-		})
-		app.Get("/p2p/ui/workers-federation-stats", auth, func(c *fiber.Ctx) error {
-			return c.SendString(elements.P2PNodeStats(p2p.GetAvailableNodes(p2p.FederatedID)))
-		})
-	}
-
 	// Show the Models page (all models)
 	app.Get("/browse", auth, func(c *fiber.Ctx) error {
 		term := c.Query("term")
@@ -118,9 +86,7 @@ func RegisterUIRoutes(app *fiber.App,
 			"AllTags":          tags,
 			"ProcessingModels": processingModelsData,
 			"AvailableModels":  len(models),
-			"IsP2PEnabled":     p2p.IsP2PEnabled(),
-
-			"TaskTypes": taskTypes,
+			"TaskTypes":        taskTypes,
 			//	"ApplicationConfig": appConfig,
 		}

@@ -269,14 +235,13 @@ func RegisterUIRoutes(app *fiber.App,

 	// Show the Chat page
 	app.Get("/chat/:model", auth, func(c *fiber.Ctx) error {
-		backendConfigs, _ := services.ListModels(cl, ml, "", true)
+		backendConfigs := cl.GetAllBackendConfigs()

 		summary := fiber.Map{
 			"Title":        "LocalAI - Chat with " + c.Params("model"),
 			"ModelsConfig": backendConfigs,
 			"Model":        c.Params("model"),
 			"Version":      internal.PrintableVersion(),
-			"IsP2PEnabled": p2p.IsP2PEnabled(),
 		}

 		// Render index
@@ -284,7 +249,7 @@ func RegisterUIRoutes(app *fiber.App,
 	})

 	app.Get("/talk/", auth, func(c *fiber.Ctx) error {
-		backendConfigs, _ := services.ListModels(cl, ml, "", true)
+		backendConfigs := cl.GetAllBackendConfigs()

 		if len(backendConfigs) == 0 {
 			// If no model is available redirect to the index which suggests how to install models
@@ -294,8 +259,7 @@ func RegisterUIRoutes(app *fiber.App,
 		summary := fiber.Map{
 			"Title":        "LocalAI - Talk",
 			"ModelsConfig": backendConfigs,
-			"Model":        backendConfigs[0],
-			"IsP2PEnabled": p2p.IsP2PEnabled(),
+			"Model":        backendConfigs[0].Name,
 			"Version":      internal.PrintableVersion(),
 		}

@@ -305,7 +269,7 @@ func RegisterUIRoutes(app *fiber.App,

 	app.Get("/chat/", auth, func(c *fiber.Ctx) error {

-		backendConfigs, _ := services.ListModels(cl, ml, "", true)
+		backendConfigs := cl.GetAllBackendConfigs()

 		if len(backendConfigs) == 0 {
 			// If no model is available redirect to the index which suggests how to install models
@@ -313,11 +277,10 @@ func RegisterUIRoutes(app *fiber.App,
 		}

 		summary := fiber.Map{
-			"Title":        "LocalAI - Chat with " + backendConfigs[0],
+			"Title":        "LocalAI - Chat with " + backendConfigs[0].Name,
 			"ModelsConfig": backendConfigs,
-			"Model":        backendConfigs[0],
+			"Model":        backendConfigs[0].Name,
 			"Version":      internal.PrintableVersion(),
-			"IsP2PEnabled": p2p.IsP2PEnabled(),
 		}

 		// Render index
@@ -332,7 +295,6 @@ func RegisterUIRoutes(app *fiber.App,
 			"ModelsConfig": backendConfigs,
 			"Model":        c.Params("model"),
 			"Version":      internal.PrintableVersion(),
-			"IsP2PEnabled": p2p.IsP2PEnabled(),
 		}

 		// Render index
@@ -353,7 +315,6 @@ func RegisterUIRoutes(app *fiber.App,
 			"ModelsConfig": backendConfigs,
 			"Model":        backendConfigs[0].Name,
 			"Version":      internal.PrintableVersion(),
-			"IsP2PEnabled": p2p.IsP2PEnabled(),
 		}

 		// Render index
@@ -368,7 +329,6 @@ func RegisterUIRoutes(app *fiber.App,
 			"ModelsConfig": backendConfigs,
 			"Model":        c.Params("model"),
 			"Version":      internal.PrintableVersion(),
-			"IsP2PEnabled": p2p.IsP2PEnabled(),
 		}

 		// Render index
@@ -388,7 +348,6 @@ func RegisterUIRoutes(app *fiber.App,
 			"Title":        "LocalAI - Generate audio with " + backendConfigs[0].Name,
 			"ModelsConfig": backendConfigs,
 			"Model":        backendConfigs[0].Name,
-			"IsP2PEnabled": p2p.IsP2PEnabled(),
 			"Version":      internal.PrintableVersion(),
 		}

--- a/Show More
+++ b/Show More