RethinkFun / 100layers
☆18Updated 3 years ago
Alternatives and similar repositories for 100layers
Users that are interested in 100layers are comparing it to the libraries listed below
Sorting:
- 一些 LLM 方面的从零复现笔记☆192Updated 2 weeks ago
- ☆109Updated 10 months ago
- Baichuan2代码的逐行解析版本,适合小白☆214Updated last year
- ☆74Updated 9 months ago
- basic framework for rag(retrieval augment generation)☆84Updated last year
- 阿里天池: 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答 baseline 80+☆103Updated last year
- 此项目完成了关于 NLP-Beginner:自然语言处理入门练习 的所有任务(文本分类、信息抽取、知识图谱、机器翻译、问答系统、文本生成、Text-to-SQL、文本纠错、文本挖掘、知识蒸馏、模型加速、OCR、TTS、Prompt、embedding等),所有代码都经过测试…☆200Updated last year
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆431Updated 2 weeks ago
- ☆142Updated 11 months ago
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆98Updated last year
- ☆67Updated last year
- qwen models finetuning☆97Updated 2 months ago
- 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…☆199Updated last year
- 通义千问VLLM推理部署DEMO☆577Updated last year
- personal chatgpt☆363Updated 5 months ago
- 基于pytorch的中文意图识别和槽位填充☆174Updated 10 months ago
- Finetune baichuan pretrained model with QLora method☆15Updated last year
- 开源SFT数据集整理,随时补充☆513Updated last year
- 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
- ☆70Updated 2 months ago
- BERT-based intent and slots detector for chatbots.☆180Updated 2 months 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☆410Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆107Updated last year
- baichuan LLM surpervised finetune by lora☆63Updated last year
- 专注于对话系统领域的技术分享,重点写《Dify应用操作和源码剖析》专栏。☆93Updated 10 months ago
- Baichuan-13B 指令微调☆90Updated last year
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆399Updated last year
- RAG 论文学习☆126Updated last month
- ☆40Updated 8 months ago
- 本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.☆249Updated 4 months ago