CoinCheung / gdGPT Star 86 Code Issues Pull requests Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp. nlp bloom pipeline pytorch deepspeed llm full-finetune model-parallization flash-attention llama2 baichuan2-7b chatglm3-6b mixtral-8x7b Updated Feb 5, 2024 Python
IAAR-Shanghai / NewsBench Star 22 Code Issues Pull requests [ACL 2024]NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism benchmark framework evaluation dataset gpt4 large-language-models llm chatgpt ernie-bot gpt35turbo chatglm2-6b xverse internlm-20b baichaun2 aquila2 qwen-14b chatglm3-6b acl2024 Updated Jun 3, 2024 Python
yucl80 / local-openai-api-service Star 4 Code Issues Pull requests LLM API Server , OpenAI 同时支持 ChatGLM3 ,Llama, Llama-3, Firefunction, Openfunctions ,BAAI/bge-m3 ,bge-large-zh-v1.5 function firefunctions openai-api llamacpp functionary chatglm3 chatglm3-6b llama3 bge-m3 Updated May 28, 2024 Python
earthonliner / SpeakEasy Star 3 Code Issues Pull requests An spoken English chatbot runs in realtime and offline based on LLM. deep-learning chatbot spoken-english llm chatglm3 chatglm3-6b oral-english Updated Apr 6, 2024 C++