LLM Models
Chinese LLMs
- Taiwan LLM
- GitHub: https://github.com/MiuLab/Taiwan-LLM
HuggingFace:HF: https://huggingface.co/yentinglinHuggingFace:HF: https://huggingface.co/audreyt
- TAIDE - Trustworthy AI Dialogue Engine
- GitHub: https://github.com/taide-taiwan
HuggingFace:HF: https://huggingface.co/taide
- 01.AI - Yi
- GitHub: https://github.com/01-ai/Yi
HuggingFace:HF: https://huggingface.co/01-ai/
- CKIP-Llama-2-7b 是中央研究院詞庫小組(CKIP)開發的開源可商用繁體中文大型語言模型,以商用開源模型Llama-2-7b以及Atom-7b為基礎,再補強繁體中文的處理能力,並對405個可商用的任務檔案同步進行訓練優化,參數量達70億(7 billion)。
- GitHub: https://github.com/f901107/CKIP-Llama-2-7b
HuggingFace:HF: https://huggingface.co/spaces/ckiplab/CKIP-Llama-2-7b-chat
- Qwen - 阿里雲通義千問
- Chinese-Mixtral
- DeepSeek - 深度求索
Code LLMs
- Granite - Open sourcing IBM’s Granite code models
HuggingHFace:F: https://huggingface.co/ibm-granite- GitHub: https://github.com/ibm-granite
- IBM開源程式開發專用Granite語言模型,效能超越當前多數開源模型 | iThome
- Codestral - Mistral's first generative AI model for code
Benchmark
- PromptBench: A Unified Library for Evaluating and Understanding Large Language Models.
Function Calling LLMs
- Firefunction-v2
HuggingFace:HF: https://huggingface.co/fireworks-ai/firefunction-v2