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。
☆223Dec 8, 2023Updated 2 years ago
Alternatives and similar repositories for llms_tool
Users that are interested in llms_tool are comparing it to the libraries listed below
Sorting:
- 百度UIE抽取模型torch版训练预测框架☆12Nov 20, 2024Updated last year
- 一个用于训练句子embedding的工具，支持Cosent以及Simcse、infonce☆21Jun 17, 2025Updated 9 months ago
- 意图槽位模型训练框架（单意图、独立槽位），使用的是JointBERT的结构进行编写，槽位提取时可以选择双指针(Binary Pointer)实体抽取和Global Pointer两种方法。☆21May 11, 2024Updated last year
- 一个使用tensorflow2.3开发的基于Bert的意图识别的自然语言理解任务Demo☆27May 11, 2024Updated last year
- 使用torch整合两种经典的指针NER抽取范式，分别是SpanBert和苏神的GlobalPointer，简单加了些tricks，配置后一键运行☆133May 29, 2024Updated last year
- 常用的一些用于图像分类的模 型demo。☆11Nov 22, 2022Updated 3 years ago
- 爬取百度贴吧、TapTap、appstore、微博官方博主上的游戏评论(基于redis_scrapy)，过滤器采用了bloomfilter。☆55Nov 15, 2018Updated 7 years ago
- LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)☆453Oct 11, 2023Updated 2 years ago
- 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、…☆6,648Oct 24, 2024Updated last year
- Tensorflow2.3的文本分类项目，支持各种分类模型，支持相关tricks。☆177Nov 28, 2024Updated last year
- share data， prompt data , pretraining data☆36Nov 30, 2023Updated 2 years ago
- Open-Retrieval Conversational Machine Reading: A new setting & OR-ShARC dataset☆13Nov 19, 2022Updated 3 years ago
- 基于Tensorflow2.3开发的NER模型，都是CRF范式，包含Bilstm(IDCNN)-CRF、Bert-Bilstm(IDCNN)-CRF、Bert-CRF，可微调预训练模型，可对抗学习，用于命名实体识别，配置后可直接运行。☆432Dec 10, 2024Updated last year
- aigc evals☆10Dec 2, 2023Updated 2 years ago
- smart chinese LLm☆19Jan 31, 2024Updated 2 years ago
- Fast instruction tuning with Llama2☆11Apr 8, 2024Updated last year
- [ACL 2024] Code for the paper "ALaRM: Align Language Models via Hierarchical Rewards Modeling"☆25Mar 28, 2024Updated last year
- 一些 LLM 方面的从零复现笔记☆246Apr 29, 2025Updated 10 months ago
- ☆16May 31, 2024Updated last year
- 中文版hf-alignment-handbook，大模型全套sft、dpo、orpo、cpt训练教程.☆15Aug 25, 2024Updated last year
- 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☆416Oct 21, 2023Updated 2 years ago
- 基于torch的，支持logits、crf、span、global_pointer四种方法的命名实体识别任务框架☆24Feb 29, 2024Updated 2 years ago
- ChatGLM-6B 指令学习|指令数据|Instruct☆653Apr 10, 2023Updated 2 years ago
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆1,019Apr 27, 2024Updated last year
- The open source implementation of DeepSeek-R1. 开源复现 DeepSeek-R1☆276Mar 10, 2025Updated last year
- 欢迎来到 "LLM-travel" 仓库！探索大语言模型（LLM）的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆374Jul 21, 2024Updated last year
- 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.☆256Aug 1, 2023Updated 2 years ago
- In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning☆35Aug 9, 2023Updated 2 years ago
- BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）☆8,286Oct 16, 2024Updated last year
- Web one-click mode full process platform, including train data upload, fine-tuning, model merge, model deploy, gpu monitor etc., no need …☆19Nov 28, 2023Updated 2 years ago
- Open Multilingual Chatbot for Everyone☆1,277Jun 8, 2025Updated 9 months ago
- 基于Llama3，通过进一步CPT，SFT，ORPO得到的中文版Llama3☆17Apr 24, 2024Updated last year
- Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集☆3,055Apr 14, 2024Updated last year
- Modified Beam Search with periodical restart☆12Sep 12, 2024Updated last year
- RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best …☆10Nov 3, 2023Updated 2 years ago
- Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训练、微调☆294Jun 7, 2024Updated last year
- Agent HITL (Human-in-the-Loop) - 一个支持人机协作的AI代理系统，基于LangChain、LangGraph和FastAPI构建☆24Jun 2, 2025Updated 9 months ago
- ⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SF…☆2,413Sep 29, 2023Updated 2 years ago
- 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）。☆360Aug 22, 2023Updated 2 years ago