Instructions to use Tockys/GemQwen-0.5B-Instruct-q4f16_1-MLC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLC-LLM
How to use Tockys/GemQwen-0.5B-Instruct-q4f16_1-MLC with MLC-LLM:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
GemQwen-0.5B-Instruct (q4f16_1, MLC/WebLLM形式)
Gemma 3 1B(日本語・文章)と Qwen2.5-Coder-0.5B(コード・論理)の2つの教師モデルの 回答を1つの生徒モデル(Qwen2.5-Coder-0.5Bベース)へ知識蒸留した融合モデル。
- 日本語タスク(要約・感想文・敬語・会話) → Gemma 3 1B が教師
- コード・アルゴリズム・計算 → Qwen2.5-Coder-0.5B が教師
- さらに「Qwen下書き→Gemma清書」のリレー合成もデータ化して焼き込み
- LoRA(rank16, 全層) → fuse → q4f16_1 量子化(MLC)
gemqwen.pages.dev のWebLLM PWAで動作。
model_libはWebLLM prebuiltの Qwen2.5-0.5B-Instruct-q4f16_1-MLC と互換(同アーキテクチャ)。
- Downloads last month
- 20
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Tockys/GemQwen-0.5B-Instruct-q4f16_1-MLC
Base model
Qwen/Qwen2.5-0.5B Finetuned
Qwen/Qwen2.5-Coder-0.5B Finetuned
Qwen/Qwen2.5-Coder-0.5B-Instruct