mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-07-05 13:57:28 -04:00
Code Issues Packages Projects Releases Wiki Activity

chore(model-gallery): ⬆️ update checksum (#10686)

Browse Source 
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
This commit is contained in:
LocalAI [bot]
2026-07-05 10:20:02 +02:00
committed by GitHub
parent 33869da527
commit deb43e56c0
1 changed files with 4 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
gallery/index.yaml
View File

@@ -3,22 +3,7 @@
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
- https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder-MTP-GGUF
description: |
# 🌟 Qwopus3.6-35B-A3B-v1
## 💡 Base Model Overview
**Qwen3.6-35B-A3B** is an advanced hybrid sparse MoE (Mixture-of-Experts) model developed by Alibaba Cloud. It features 35B total parameters with only 3B active parameters per token, ensuring high inference efficiency. Architecturally, it combines Gated DeltaNet linear attention with standard gated attention layers, routing tokens across **256 experts**. It natively supports a massive **262k context window** and is specifically designed for high-performance agentic coding, deep reasoning, and multimodal tasks.
## 🚀 Model Refinement & Logic Tuning （Qwopus3.6-35B-A3B-v1）
🪐**Qwopus3.6-35B-A3B-v1** is a reasoning-enhanced MoE (Mixture of Experts) model fine-tuned on top of **Qwen3.6-35B-A3B**.
### 🛠 Training Strategy
The fine-tuning process for this model is structured into **three distinct stages of distributed SFT (Supervised Fine-Tuning)**, progressively scaling reasoning complexity and data diversity. This systematic approach ensures the model inherits the base MoE capabilities while sharpening its logic-handling depth.
...
description: "# \U0001F31F Qwopus3.6-35B-A3B-v1\n\n## \U0001F4A1 Base Model Overview\n\n**Qwen3.6-35B-A3B** is an advanced hybrid sparse MoE (Mixture-of-Experts) model developed by Alibaba Cloud. It features 35B total parameters with only 3B active parameters per token, ensuring high inference efficiency. Architecturally, it combines Gated DeltaNet linear attention with standard gated attention layers, routing tokens across **256 experts**. It natively supports a massive **262k context window** and is specifically designed for high-performance agentic coding, deep reasoning, and multimodal tasks.\n\n## \U0001F680 Model Refinement & Logic Tuning （Qwopus3.6-35B-A3B-v1）\n\n\U0001FA90**Qwopus3.6-35B-A3B-v1** is a reasoning-enhanced MoE (Mixture of Experts) model fine-tuned on top of **Qwen3.6-35B-A3B**.\n\n### \U0001F6E0 Training Strategy\n\nThe fine-tuning process for this model is structured into **three distinct stages of distributed SFT (Supervised Fine-Tuning)**, progressively scaling reasoning complexity and data diversity. This systematic approach ensures the model inherits the base MoE capabilities while sharpening its logic-handling depth.\n\n...\n"
license: "apache-2.0"
tags:
- llm
@@ -55,34 +40,7 @@
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
- https://huggingface.co/protoLabsAI/Ornith-1.0-9B-MTP-GGUF
description: |
[](https://deep-reinforce.com/ornith.html)
# Ornith-1.0-9B
Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.
Highlights:
- **State-of-the-Art Coding Agents**: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw.
- **Self-Improving Training Framework**:  Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model discovers better search trajectories and generates higher-quality solutions.
- **Licence**: MIT licensed, globally accessible, and free from regional limitations.
## Ornith 1.0 9B
This model card documents **Ornith-1.0-9B**, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment.
### Benchmarks
Ornith-1.0-9B
Qwen3.5-9B
Qwen3.5-35B
Gemma4-12B
Gemma4-31B
Agentic Coding
...
description: "[](https://deep-reinforce.com/ornith.html)\n\n# Ornith-1.0-9B\n\nAloha! \U0001F33A Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.\n\nHighlights:\n\n - **State-of-the-Art Coding Agents**: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw.\n - **Self-Improving Training Framework**:  Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model discovers better search trajectories and generates higher-quality solutions.\n - **Licence**: MIT licensed, globally accessible, and free from regional limitations.\n\n## Ornith 1.0 9B\n\nThis model card documents **Ornith-1.0-9B**, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment.\n\n### Benchmarks\n\nOrnith-1.0-9B\nQwen3.5-9B\nQwen3.5-35B\nGemma4-12B\nGemma4-31B\n\nAgentic Coding\n\n...\n"
license: "mit"
tags:
- llm
@@ -36066,7 +36024,7 @@
files:
- filename: parakeet-tdt-0.6b-ja.gguf
uri: huggingface://cstr/parakeet-tdt-0.6b-ja-GGUF/parakeet-tdt-0.6b-ja.gguf
sha256: a9c43116b180b8a2ada2771ac829cf751b9e73adcbe69b7c8379593f9e5da31e
sha256: 374eb0132eebaec4df77a9631cbbeb03790be48a4a517f6cc8e8bdb38fe9a584
- name: parakeet-tdt-1.1b-crispasr
url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls:
@@ -36525,7 +36483,7 @@
files:
- filename: vibevoice-realtime-0.5b-q4_k.gguf
uri: huggingface://cstr/vibevoice-realtime-0.5b-GGUF/vibevoice-realtime-0.5b-q4_k.gguf
sha256: e3244986d8939a9a8f65701196efbfe3f8b81afd307b29f434fe259b9c411ef1
sha256: 483e1922a9077e3fc66b7947a4d6fee3dfd8edc30afde3410efa5bb386bc0392
- name: chatterbox-tts-crispasr
url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls: