FreedomIntelligence / InstructionZooLinks
☆281Updated last year
Alternatives and similar repositories for InstructionZoo
Users that are interested in InstructionZoo are comparing it to the libraries listed below
Sorting:
- ☆459Updated last year
- ☆307Updated 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
- 语言模型中文认知能力分析☆236Updated last year
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆236Updated 2 years ago
- pCLUE: 1000000+多任务提示学习数据集☆498Updated 2 years ago
- Implementation of Chinese ChatGPT☆285Updated last year
- ☆162Updated 2 years ago
- alpaca中文指令微调数据集☆392Updated 2 years ago
- 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
- 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
- Naive Bayes-based Context Extension☆326Updated 7 months ago
- 中文 Instruction tuning datasets☆132Updated last year
- A framework for cleaning Chinese dialog data☆272Updated 4 years ago
- Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.☆606Updated 5 months ago
- ChatGLM-6B 指令学习|指令数据|Instruct☆653Updated 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
- 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）。☆360Updated last year
- Baichuan2代码的逐行解析版本，适合小白☆214Updated last year
- 开源SFT数据集整理,随时补充☆523Updated 2 years ago
- 中文图书语料MD5链接☆217Updated last year
- 大语言模型指令调优工具（支持 FlashAttention）☆174Updated last year
- A Chinese Open-Domain Dialogue System☆321Updated last year
- ☆172Updated 2 years ago
- ☆170Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆114Updated 2 years ago
- chatglm多gpu用deepspeed和☆409Updated 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。☆216Updated last year
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆375Updated 2 weeks ago
- text embedding☆146Updated last year