BaileyWei's Stars
cybertronai/gradient-checkpointing
Make huge neural nets fit in memory
shibing624/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型,实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
LinkSoul-AI/LLaSM
第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验,同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。
DUOMO/TransGPT
huggingface/trl
Train transformer language models with reinforcement learning.
joonspk-research/generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
LlamaFamily/Llama-Chinese
Llama中文社区,Llama3在线体验和微调模型已开放,实时汇总最新Llama3学习资料,已将所有代码更新适配Llama3,构建最好的中文Llama大模型,完全开源可商用
meta-llama/llama-recipes
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.
OptimalScale/LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
TeSaiFa/llm-auto-eval
guodongxiaren/README
README文件语法解读,即Github Flavored Markdown语法介绍
guidance-ai/guidance
A guidance language for controlling large language models.
sunnweiwei/RankGPT
Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]
llmeval/llmeval-1
中文大语言模型评测第一期
ztxz16/fastllm
纯c++的全平台llm加速库,支持python调用,chatglm-6B级模型单卡可达10000+token / s,支持glm, llama, moss基座,手机端流畅运行
PKU-YuanGroup/ChatLaw
ChatLaw:A Powerful LLM Tailored for Chinese Legal. 中文法律大模型
jeinlee1991/chinese-llm-benchmark
中文大模型能力评测榜单:目前已囊括115个大模型,覆盖chatgpt、gpt4o、百度文心一言、阿里通义千问、讯飞星火、商汤senseChat、minimax等商用模型, 以及百川、qwen2、glm4、yi、书生internLM2、llama3等开源大模型,多维度能力评测。不仅提供能力评分排行榜,也提供所有模型的原始输出结果!
ssbuild/chatglm2_finetuning
chatglm2 6b finetuning and alpaca finetuning
inverse-scaling/prize
A prize for finding tasks that cause large language models to show inverse scaling
OpenLMLab/GAOKAO-Bench
GAOKAO-Bench is an evaluation framework that utilizes GAOKAO questions as a dataset to evaluate large language models.
ExpressAI/AI-Gaokao
Gaokao Benchmark for AI
THUDM/ChatGLM2-6B
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
Facico/Chinese-Vicuna
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
liucongg/ChatGLM-Finetuning
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等
yangjianxin1/Firefly
Firefly: 大模型训练工具,支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
yuchenlin/LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
qwopqwop200/GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ
bitsandbytes-foundation/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
hikariming/chat-dataset-baseline
人工精调的中文对话数据集和一段chatglm的微调代码