schinger / FullLLMLinks
Full stack LLM (Pre-training/finetuning, PPO(RLHF), Inference, Quant, etc.)
☆27Updated 7 months ago
Alternatives and similar repositories for FullLLM
Users that are interested in FullLLM are comparing it to the libraries listed below
Sorting:
- Reinforcement Learning in LLM and NLP.☆56Updated 2 weeks ago
- 在verl上做reward的定制开发☆116Updated 4 months ago
- 基于DPO算法微调语言大模型,简单好上手。☆45Updated last year
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆255Updated 7 months ago
- Train your grpo with zero dataset and low resources, 8bit/4bit/lora/qlora supported, multi-gpu supported ...☆78Updated 4 months ago
- The related works and background techniques about Openai o1☆222Updated 8 months ago
- This is a repo for showcasing using MCTS with LLMs to solve gsm8k problems☆91Updated 6 months ago
- a-m-team's exploration in large language modeling☆188Updated 3 months ago
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆65Updated 7 months ago
- ☆115Updated 10 months ago
- ☆147Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆114Updated 2 years ago
- ☆145Updated last year
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆136Updated 2 months ago
- llm & rl☆218Updated last week
- Fantastic Data Engineering for Large Language Models☆91Updated 8 months ago
- ☆129Updated last year
- ☆47Updated 7 months ago
- ☆159Updated 8 months ago
- 使用单个24G显卡,从0开始训练LLM☆55Updated 2 months ago
- 怎么训练一个LLM分词器☆153Updated 2 years ago
- ☆83Updated last year
- ☆96Updated 9 months ago
- ☆19Updated last year
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Updated 9 months ago
- ☆125Updated last year
- RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.☆73Updated 7 months ago
- LeetCode Training and Evaluation Dataset☆34Updated 5 months ago
- Collection of papers for scalable automated alignment.☆93Updated 11 months ago
- 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。☆95Updated last year