mirror/LocalAI
1
0 Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-10-28 09:08:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat(gallery): add LFM2.5 dynamic variants

Browse Source 
Offer Unsloth dynamic Q4 and Q6 builds alongside the official GGUFs.
Pin their revisions and verify hashes through two Hugging Face sources.

Assisted-by: Codex:gpt-6

(cherry picked from commit ab8d685f01, mudler/LocalAI#12774)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
localai-org-maint-bot authored and Ettore Di Giacinto committed 2026-10-25 09:55:39 +00:00
1 parent f73e30effa
commit a0b4af9369
2 files changed
+180
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

gallery/index.yaml
+82
View File
@@ -3,6 +3,86 @@
# written by scripts/models/cmd/modelcatalog and stays only so releases before
# the cutover keep working. CI fails when it differs from the generated copy:
# go run ./scripts/models/cmd/modelcatalog --library gallery/models/index.yaml --out gallery/index.yaml
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: lfm2.5-24b-a2b-ud-q4
description: |
LiquidAI LFM2.5-24B-A2B is a text-only reasoning model with 24B total
parameters and 2.45B active parameters for multilingual chat and tool use.
This entry uses Unsloth's dynamic UD-Q4_K_XL GGUF quantization.
license: other
urls:
- https://huggingface.co/LiquidAI/LFM2.5-24B-A2B
- https://huggingface.co/unsloth/LFM2.5-24B-A2B-GGUF
icon: https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png
tags:
- llm
- gguf
- reasoning
- cpu
- gpu
files:
- filename: llama-cpp/models/unsloth/LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-UD-Q4_K_XL.gguf
sha256: a235d23638cc5549cb1ff61da7522c8a7e97f056f27093462a1e56f35aba91d8
uri: https://huggingface.co/unsloth/LFM2.5-24B-A2B-GGUF/resolve/faa77113e93335b63423e9e8d33395f86eaf8946/LFM2.5-24B-A2B-UD-Q4_K_XL.gguf
overrides:
backend: llama-cpp
context_size: 131072
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
- completion
options:
- use_jinja:true
parameters:
model: llama-cpp/models/unsloth/LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-UD-Q4_K_XL.gguf
repeat_penalty: 1.05
temperature: 0.1
top_k: 50
template:
use_tokenizer_template: true
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: lfm2.5-24b-a2b-ud-q6
description: |
LiquidAI LFM2.5-24B-A2B is a text-only reasoning model with 24B total
parameters and 2.45B active parameters for multilingual chat and tool use.
This entry uses Unsloth's dynamic UD-Q6_K_XL GGUF quantization.
license: other
urls:
- https://huggingface.co/LiquidAI/LFM2.5-24B-A2B
- https://huggingface.co/unsloth/LFM2.5-24B-A2B-GGUF
icon: https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png
tags:
- llm
- gguf
- reasoning
- cpu
- gpu
files:
- filename: llama-cpp/models/unsloth/LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-UD-Q6_K_XL.gguf
sha256: abcb7e21e006eb4c826a2b75fb91c0804db7b20f908a61beeebdbdd07c88f41d
uri: https://huggingface.co/unsloth/LFM2.5-24B-A2B-GGUF/resolve/faa77113e93335b63423e9e8d33395f86eaf8946/LFM2.5-24B-A2B-UD-Q6_K_XL.gguf
overrides:
backend: llama-cpp
context_size: 131072
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
- completion
options:
- use_jinja:true
parameters:
model: llama-cpp/models/unsloth/LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-UD-Q6_K_XL.gguf
repeat_penalty: 1.05
temperature: 0.1
top_k: 50
template:
use_tokenizer_template: true
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: ternary-bonsai-2-2b
description: |
@@ -19569,6 +19649,8 @@
template:
use_tokenizer_template: true
variants:
- model: lfm2.5-24b-a2b-ud-q4
- model: lfm2.5-24b-a2b-ud-q6
- model: lfm2.5-24b-a2b-q5
- model: lfm2.5-24b-a2b-q6
- model: lfm2.5-24b-a2b-q8
gallery/models/index.yaml
+98
View File
@@ -4,6 +4,102 @@
# changes and never edit it by hand. CI fails when it is stale. A build from
# master reads it as the default model source; a tagged build reads the gallery
# until the release cutover.
- kind: model
id: lfm2.5-24b-a2b-ud-q4
name: lfm2.5-24b-a2b-ud-q4
version: 0.0.0-gallery.fbd02ecf6f42
description: |
LiquidAI LFM2.5-24B-A2B is a text-only reasoning model with 24B total
parameters and 2.45B active parameters for multilingual chat and tool use.
This entry uses Unsloth's dynamic UD-Q4_K_XL GGUF quantization.
license: other
urls:
- https://huggingface.co/LiquidAI/LFM2.5-24B-A2B
- https://huggingface.co/unsloth/LFM2.5-24B-A2B-GGUF
tags:
- llm
- gguf
- reasoning
- cpu
- gpu
icon: https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: llama-cpp/models/unsloth/LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-UD-Q4_K_XL.gguf
sha256: a235d23638cc5549cb1ff61da7522c8a7e97f056f27093462a1e56f35aba91d8
uri: https://huggingface.co/unsloth/LFM2.5-24B-A2B-GGUF/resolve/faa77113e93335b63423e9e8d33395f86eaf8946/LFM2.5-24B-A2B-UD-Q4_K_XL.gguf
overrides:
backend: llama-cpp
context_size: 131072
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
- completion
options:
- use_jinja:true
parameters:
model: llama-cpp/models/unsloth/LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-UD-Q4_K_XL.gguf
repeat_penalty: 1.05
temperature: 0.1
top_k: 50
template:
use_tokenizer_template: true
- kind: model
id: lfm2.5-24b-a2b-ud-q6
name: lfm2.5-24b-a2b-ud-q6
version: 0.0.0-gallery.863d8f36da1e
description: |
LiquidAI LFM2.5-24B-A2B is a text-only reasoning model with 24B total
parameters and 2.45B active parameters for multilingual chat and tool use.
This entry uses Unsloth's dynamic UD-Q6_K_XL GGUF quantization.
license: other
urls:
- https://huggingface.co/LiquidAI/LFM2.5-24B-A2B
- https://huggingface.co/unsloth/LFM2.5-24B-A2B-GGUF
tags:
- llm
- gguf
- reasoning
- cpu
- gpu
icon: https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: llama-cpp/models/unsloth/LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-UD-Q6_K_XL.gguf
sha256: abcb7e21e006eb4c826a2b75fb91c0804db7b20f908a61beeebdbdd07c88f41d
uri: https://huggingface.co/unsloth/LFM2.5-24B-A2B-GGUF/resolve/faa77113e93335b63423e9e8d33395f86eaf8946/LFM2.5-24B-A2B-UD-Q6_K_XL.gguf
overrides:
backend: llama-cpp
context_size: 131072
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
- completion
options:
- use_jinja:true
parameters:
model: llama-cpp/models/unsloth/LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-UD-Q6_K_XL.gguf
repeat_penalty: 1.05
temperature: 0.1
top_k: 50
template:
use_tokenizer_template: true
- kind: model
id: ternary-bonsai-2-2b
name: ternary-bonsai-2-2b
@@ -22850,6 +22946,8 @@
template:
use_tokenizer_template: true
variants:
- model: lfm2.5-24b-a2b-ud-q4
- model: lfm2.5-24b-a2b-ud-q6
- model: lfm2.5-24b-a2b-q5
- model: lfm2.5-24b-a2b-q6
- model: lfm2.5-24b-a2b-q8