binmakeswell / ColossalChatLinks
ColossalChat is the project to implement LLM with RLHF, powered by the Colossal-AI project.
☆69Updated last year
Alternatives and similar repositories for ColossalChat
Users that are interested in ColossalChat are comparing it to the libraries listed below
Sorting:
- chatglm-6b微调/LORA/PPO/推理, 样本为自动生成的整数/小数加减乘除运算, 可gpu/cpu☆164Updated last year
- llama inference for tencentpretrain☆98Updated 2 years ago
- 实现一种多Lora权值集成切换+Zero-Finetune零微调增强的跨模型技术方案，LLM-Base+LLM-X+Alpaca，初期，LLM-Base为Chatglm6B底座模型，LLM-X是LLAMA增强模型。该方案简易高效，目标是使此类语言模型能够低能耗广泛部署，并最…☆116Updated last year
- deep learning☆148Updated 2 months ago
- 全球首个StableVicuna中文优化版。☆64Updated 2 years ago
- 骆驼QA，中文大语言阅读理解模型。☆74Updated 2 years ago
- 使用qlora对中文大语言模型进行微调，包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE☆87Updated 2 years ago
- 用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.☆253Updated last year
- The official repo of Aquila2 series proposed by BAAI, including pretrained & chat large language models.☆444Updated 9 months ago
- ☆307Updated 2 years ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆108Updated last year
- alpaca中文指令微调数据集☆392Updated 2 years ago
- Simple implementation of using lora form the peft library to fine-tune the chatglm-6b☆83Updated 2 years ago
- 旨在对当前主流LLM进行一个直观、具体、标准的评测☆94Updated 2 years ago
- chatglm多gpu用deepspeed和☆407Updated last year
- Baichuan2代码的逐行解析版本，适合小白☆214Updated last year
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆195Updated 2 years ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆136Updated 7 months ago
- 大语言模型指令调优工具（支持 FlashAttention）☆174Updated last year
- ChatGLM-6B fine-tuning.☆135Updated 2 years ago
- Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆409Updated last year
- 微调ChatGLM☆126Updated 2 years ago
- “悟道”模型☆122Updated 3 years ago
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆236Updated 2 years ago
- （1）弹性区间标准化的旋转位置词嵌入编码器+peft LORA量化训练，提高万级tokens性能支持。（2）证据理论解释学习，提升模型的复杂逻辑推理能力（3）兼容alpaca数据格式。☆44Updated last year
- ☆105Updated last year
- A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Huma…☆136Updated 2 years ago
- 一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。☆217Updated last year
- Luotuo Embedding(骆驼嵌入) is a text embedding model, which developed by 李鲁鲁, 冷子昂, 陈启源, 蒟蒻等.☆266Updated last year
- Humanable Chat Generative-model Fine-tuning | LLM微调☆207Updated last year