schinger / FullLLM
Full stack LLM (Pre-training/finetuning, PPO(RLHF), Inference, Quant, etc.)
☆17Updated last month
Alternatives and similar repositories for FullLLM:
Users that are interested in FullLLM are comparing it to the libraries listed below
- 基于DPO算法微调语言大模型,简单好上手。☆35Updated 8 months ago
- ☆66Updated last year
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆62Updated last month
- pytorch分布式训练☆64Updated last year
- ☆34Updated last month
- 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答, 75+ baseline☆56Updated last year
- NTK scaled version of ALiBi position encoding in Transformer.☆67Updated last year
- 使用单个24G显卡,从0开始训练LLM☆50Updated 5 months ago
- ☆15Updated last year
- llama,chatglm 等模型的微调☆86Updated 8 months ago
- A research repo for experiments about Reinforcement Finetuning☆37Updated 2 weeks ago
- The implementation of paper "LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Fee…☆38Updated 8 months ago
- 记录NLP、CV、搜索、推荐等AI岗位最新情况。☆29Updated 2 years ago
- ☆40Updated 7 months ago
- ☆137Updated 11 months ago
- 怎么训练一个LLM分词器☆142Updated last year
- self-adaptive in-context learning☆43Updated last year
- This is the code repo for the paper <UTC-IE: A Unified Token-pair Classification Architecture for Information Extraction>☆15Updated last year
- ☆81Updated last year
- 擂台赛3-大规模预训练调优比赛的示例代码与baseline实现☆38Updated 2 years ago
- A curated list of awesome works in Routing LLMs paradigm (👉 Welcome to submit your contributions to this code repository)☆16Updated last week
- 基于python的BM25文本匹配算法实现☆31Updated 2 years ago
- ☆122Updated last year
- A Transformer Framework Based Couplet Task☆24Updated last year
- [ICML'2024] Can AI Assistants Know What They Don't Know?☆79Updated last year
- 本项目用于大模型数学解题能力方面的数据集合成,模型训练及评测,相关文章记录。☆80Updated 6 months ago
- Repo for ACL2023 paper "Plug-and-Play Knowledge Injection for Pre-trained Language Models"☆60Updated last year
- ☆142Updated 9 months ago
- [Findings of EMNLP'2024] Unified Active Retrieval for Retrieval Augmented Generation☆21Updated 6 months ago
- SuperCLUE-Math6:新一代中文原生多轮多步数学推理数据集的探索之旅☆53Updated last year