open-chinese / alpaca-chinese-dataset

Related projects ⓘ

Alternatives and complementary repositories for alpaca-chinese-dataset

• ArtificialZeng / Baichuan2-Explained
  Baichuan2代码的逐行解析版本，适合小白
  ☆208Updated last year
• yangjianxin1 / Firefly-LLaMA2-Chinese
  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
  ☆399Updated last year
• yongzhuo / LLM-SFT
  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…
  ☆169Updated 6 months ago
• SupritYoung / RLHF-Label-Tool
  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.
  ☆243Updated last year
• modelscope / evalscope
  A streamlined and customizable framework for efficient large model evaluation and performance benchmarking
  ☆262Updated this week
• Logistic98 / rag-omni
  基于BM25、BGE的检索增强生成RAG示例
  ☆99Updated 3 weeks ago
• xubuvd / LLMs
  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。
  ☆112Updated 2 months ago
• jiahe7ay / MINI_LLM
  This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.
  ☆356Updated 6 months ago
• shuxueslpi / chatGLM-6B-QLoRA
  使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。
  ☆356Updated last year
• wenge-research / YAYI-UIE
  雅意信息抽取大模型：在百万级人工构造的高质量信息抽取数据上进行指令微调，由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)
  ☆270Updated 3 months ago
• stanleylsx / llms_tool
  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。
  ☆203Updated 11 months ago
• zejunwang1 / LLMTuner
  大语言模型指令调优工具（支持 FlashAttention）
  ☆166Updated 10 months ago
• yangjianxin1 / LLMPruner
  ☆297Updated last year
• ssbuild / qwen_finetuning
  qwen-7b and qwen-14b finetuning
  ☆84Updated 7 months ago
• percent4 / embedding_rerank_retrieval
  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.
  ☆179Updated 3 months ago
• zhanshijinwat / Steel-LLM
  Train a 1B LLM with 1T tokens from scratch by personal
  ☆337Updated this week
• twang2218 / vocab-coverage
  语言模型中文认知能力分析
  ☆234Updated last year
• yuanzhoulvpi2017 / SentenceEmbedding
  ☆88Updated 4 months ago
• SpongebBob / Finetune-ChatGLM2-6B
  ChatGLM2-6B 全参数微调，支持多轮对话的高效微调。
  ☆395Updated last year
• charent / Phi2-mini-Chinese
  Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.
  ☆489Updated 4 months ago
• yongzhuo / ChatGLM2-SFT
  ChatGLM2-6B微调, SFT/LoRA, instruction finetune
  ☆106Updated last year
• Chinese-Tiny-LLM / Chinese-Tiny-LLM
  ☆213Updated 6 months ago
• NLPJCL / RAG-Retrieval
  Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.
  ☆513Updated last week
• yanqiangmiffy / how-to-train-tokenizer
  怎么训练一个LLM分词器
  ☆130Updated last year
• BUAADreamer / EasyRAG
  Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案
  ☆127Updated this week
• wp931120 / baichuan_sft_lora
  baichuan LLM surpervised finetune by lora
  ☆60Updated last year
• SupritYoung / Zhongjing
  A Chinese medical ChatGPT based on LLaMa, training from large-scale pretrain corpus and multi-turn dialogue dataset.
  ☆318Updated 11 months ago
• QwenLM / vllm-gptq
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆124Updated 11 months ago
• the-seeds / imitater
  Imitate OpenAI with Local Models
  ☆85Updated 2 months ago
• liangwq / Chatglm_lora_multi-gpu
  chatglm多gpu用deepspeed和
  ☆403Updated 4 months ago