Skip to content

chore(model gallery): 🤖 add 1 new models via gallery agent #6894

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

chore(model gallery): 🤖 add 1 new models via gallery agent #6894

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 24 additions & 0 deletions gallery/index.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3127,7 +3127,7 @@
- gemma3
- gemma-3
overrides:
#mmproj: gemma-3-27b-it-mmproj-f16.gguf

Check warning on line 3130 in gallery/index.yaml

View workflow job for this annotation

GitHub Actions / Yamllint 

3130:6 [comments] missing starting space in comment
parameters:
model: gemma-3-27b-it-Q4_K_M.gguf
files:
Expand All @@ -3145,7 +3145,7 @@
description: |
google/gemma-3-12b-it is an open-source, state-of-the-art, lightweight, multimodal model built from the same research and technology used to create the Gemini models. It is capable of handling text and image input and generating text output. It has a large context window of 128K tokens and supports over 140 languages. The 12B variant has been fine-tuned using the instruction-tuning approach. Gemma 3 models are suitable for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes them deployable in environments with limited resources such as laptops, desktops, or your own cloud infrastructure.
overrides:
#mmproj: gemma-3-12b-it-mmproj-f16.gguf

Check warning on line 3148 in gallery/index.yaml

View workflow job for this annotation

GitHub Actions / Yamllint 

3148:6 [comments] missing starting space in comment
parameters:
model: gemma-3-12b-it-Q4_K_M.gguf
files:
Expand All @@ -3163,7 +3163,7 @@
description: |
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. Gemma-3-4b-it is a 4 billion parameter model.
overrides:
#mmproj: gemma-3-4b-it-mmproj-f16.gguf

Check warning on line 3166 in gallery/index.yaml

View workflow job for this annotation

GitHub Actions / Yamllint 

3166:6 [comments] missing starting space in comment
parameters:
model: gemma-3-4b-it-Q4_K_M.gguf
files:
Expand Down Expand Up @@ -6781,7 +6781,7 @@
sha256: 2756551de7d8ff7093c2c5eec1cd00f1868bc128433af53f5a8d434091d4eb5a
uri: huggingface://Triangle104/Nano_Imp_1B-Q8_0-GGUF/nano_imp_1b-q8_0.gguf
- &qwen25
name: "qwen2.5-14b-instruct" ## Qwen2.5

Check warning on line 6784 in gallery/index.yaml

View workflow job for this annotation

GitHub Actions / Yamllint 

6784:32 [comments] too few spaces before comment: expected 2
icon: https://avatars.githubusercontent.com/u/141221163
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
license: apache-2.0
Expand Down Expand Up @@ -22950,3 +22950,27 @@
- filename: apollo-astralis-4b.i1-Q4_K_M.gguf
sha256: 94e1d371420b03710fc7de030c1c06e75a356d9388210a134ee2adb4792a2626
uri: huggingface://mradermacher/apollo-astralis-4b-i1-GGUF/apollo-astralis-4b.i1-Q4_K_M.gguf
- !!merge <<: *qwen25coder
name: "viscoder2-7b-i1"
urls:
- https://huggingface.co/mradermacher/VisCoder2-7B-i1-GGUF
description: |
**VisCoder2-7B** is a lightweight, multi-language visualization coding model designed for generating executable code that produces accurate and consistent visual outputs. Trained on the **VisCode-Multi-679K** dataset—spanning 12 programming languages—it excels at turning natural language instructions into functional visualization code, with strong support for iterative self-debugging.

Built on **Qwen2.5-Coder-7B-Instruct**, the model is fine-tuned via full-parameter supervised fine-tuning to align code execution with visual intent, making it ideal for tasks like plotting, data visualization, and interactive diagram generation across diverse programming environments.

**Key Features:**
- ✅ Generates **executable code** that renders correctly
- ✅ Supports **12 programming languages**
- ✅ Trained for **multi-turn self-debugging**
- ✅ Evaluates strongly on **VisPlotBench**, a benchmark for visualization tasks

Perfect for developers, researchers, and AI agents working on visual coding challenges.
👉 [Read the paper](https://arxiv.org/abs/2510.23642) | [Explore on Hugging Face](https://huggingface.co/TIGER-Lab/VisCoder2-7B) | [GitHub Repo](https://github.com/TIGER-AI-Lab/VisCoder2)
overrides:
parameters:
model: VisCoder2-7B.i1-Q4_K_M.gguf
files:
- filename: VisCoder2-7B.i1-Q4_K_M.gguf
sha256: 4aa2a6a00ba17e49b273d70c0361c3ef76f76795a714e5ca20dd5b1f3a86ebdb
uri: huggingface://mradermacher/VisCoder2-7B-i1-GGUF/VisCoder2-7B.i1-Q4_K_M.gguf
Loading