lansinuote / Simple_TRL
☆15Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for Simple_TRL
- ChatGLM-6B添加了RLHF的实现,以及部分核心代码的逐行讲解 ,实例部分是做了个新闻短标题的生成,以及指定context推荐的RLHF的实现☆78Updated last year
- 使用单个24G显卡,从0开始训练LLM☆49Updated 2 weeks ago
- 怎么训练一个LLM分词器☆129Updated last year
- ☆87Updated 4 months ago
- ☆62Updated 11 months ago
- ☆23Updated last year
- 大语言模型应用:RAG、NL2SQL、聊天机器人、预训练、MOE混合专家模型、微调训练、强化学习、天池数据竞赛☆49Updated 4 months ago
- 基于DPO算法微调语言大模型,简单好上手。☆28Updated 4 months ago
- 使用sentencepiece中BPE训练中文词表,并在transformers中进行使用。☆109Updated last year
- ☆11Updated last month
- ☆118Updated 6 months ago
- ☆36Updated 3 months ago
- 通义千问的DPO训练☆25Updated last month
- 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。☆202Updated 11 months ago
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆68Updated 5 months ago
- personal chatgpt☆317Updated this week
- Train a Chinese LLM From 0 by Personal☆199Updated last week
- Inference code for LLaMA models☆107Updated last year
- 本项目是自动化学报中AUTOPLAN的代码地址,使用大语言模型完成了复杂任务的任务规划以及任务执行☆74Updated this week
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆99Updated last year
- ☆25Updated this week
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆189Updated last year
- Scripts of LLM pre-training and fine-tuning (w/wo LoRA, DeepSpeed)☆68Updated 9 months ago
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆305Updated 2 months ago
- DeepSpeed Tutorial☆89Updated 2 months ago
- 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+☆73Updated 10 months ago
- 大语言模型指令调优工具(支持 FlashAttention)☆166Updated 10 months ago
- llama,chatglm 等模型的微调☆82Updated 3 months ago
- pytorch分布式训练☆58Updated last year
- ☆52Updated this week