ssbuild / baichuan_finetuningLinks
baichuan and baichuan2 finetuning and alpaca finetuning
☆32Updated 4 months ago
Alternatives and similar repositories for baichuan_finetuning
Users that are interested in baichuan_finetuning are comparing it to the libraries listed below
Sorting:
- qwen models finetuning☆100Updated 4 months ago
- Baichuan2代码的逐行解析版本,适合小白☆214Updated last year
- 专注于中文领域大语 言模型,落地到某个行业某个领域,成为一个行业大模型、公司级别或行业级别领域大模型。☆119Updated 4 months 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
- 大语言模型指令调优工具(支持 FlashAttention)☆174Updated last year
- 怎么训练一个LLM分词器☆151Updated 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
- 使用sentencepiece中BPE训练中文词表,并在transformers中进行使用。☆118Updated 2 years ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆108Updated last year
- Baichuan-13B 指令微调☆90Updated 2 years ago
- llama inference for tencentpretrain☆98Updated 2 years ago
- 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
- deep learning☆148Updated 2 months ago
- Generate dialog data from documents using LLM like ChatGLM2 or ChatGPT;利用ChatGLM2,ChatGPT等大模型根据文档生成对话数据集☆158Updated last year
- 中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微…☆206Updated last year
- 语言模型中文认知能力分析☆236Updated last year
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆63Updated last year
- 骆驼QA,中文大语言阅读理解模型。☆74Updated 2 years ago
- chatglm多gpu用deepspeed和☆407Updated last year
- deepspeed+trainer简单高效实现多卡微调大模型☆126Updated 2 years ago
- ☆307Updated 2 years ago
- Alpaca Chinese Dataset -- 中文指令微调数据集☆209Updated 9 months ago
- Simple implementation of using lora form the peft library to fine-tune the chatglm-6b☆83Updated 2 years ago
- 📔 对Chinese-LLaMA-Alpaca进行使用说明和核心代码注解☆49Updated 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
- 中文书籍收录整理, Collection of Chinese Books☆189Updated last year
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆47Updated last year
- baichuan LLM surpervised finetune by lora☆63Updated 2 years ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆136Updated 7 months ago