xyjigsaw / LLM-Pretrain-SFT
Scripts of LLM pre-training and fine-tuning (w/wo LoRA, DeepSpeed)
☆67Updated 7 months ago
Related projects: ⓘ
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆61Updated 4 months ago
- ☆109Updated 5 months ago
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆281Updated 2 weeks ago
- 🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.☆128Updated 2 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆196Updated last year
- ☆46Updated 2 months ago
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆58Updated last year
- LongAlign: A Recipe for Long Context Alignment Encompassing Data, Training, and Evaluation☆194Updated 4 months ago
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆105Updated 3 months ago
- 使用单个24G显卡,从0开始训练LLM☆47Updated 2 months ago
- 怎么训练一个LLM分词器☆123Updated last year
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆101Updated 2 weeks ago
- Awesome papers for role-playing with language models☆88Updated last month
- 基于DPO算法微调语言大模型,简单好上手。☆24Updated 2 months ago
- ☆111Updated 6 months ago
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆37Updated 6 months ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆106Updated last year
- [SIGIR'24] The official implementation code of MOELoRA.☆113Updated last month
- ☆71Updated 8 months ago
- Code for "FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models (ACL 2024)"☆80Updated last week
- A collection for math word problem (MWP) works, including datasets, algorithms and so on.☆28Updated 3 months ago
- ☆124Updated 2 months ago
- ☆89Updated 9 months ago
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆151Updated 6 months ago
- ☆148Updated 10 months ago
- deepspeed+trainer简单高效实现多卡微调大模型☆115Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆162Updated 8 months ago
- ☆77Updated 2 months ago
- ☆87Updated 4 months ago
- ☆90Updated 6 months ago