xyjigsaw / LLM-Pretrain-SFTLinks
Scripts of LLM pre-training and fine-tuning (w/wo LoRA, DeepSpeed)
☆87Updated last year
Alternatives and similar repositories for LLM-Pretrain-SFT
Users that are interested in LLM-Pretrain-SFT are comparing it to the libraries listed below
Sorting:
- 🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.☆138Updated 8 months ago
- 怎么训练一个LLM分词器☆154Updated 2 years ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆90Updated last year
- ☆125Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆116Updated 2 years ago
- LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA☆235Updated 4 months ago
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆67Updated 2 years ago
- realize the reinforcement learning training for gpt2 llama bloom and so on llm model☆26Updated 2 years ago
- Fantastic Data Engineering for Large Language Models☆93Updated last year
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆184Updated 6 months ago
- ☆147Updated last year
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆225Updated 2 years ago
- Official Repository for SIGIR2024 Demo Paper "An Integrated Data Processing Framework for Pretraining Foundation Models"☆85Updated last year
- Collection of training data management explorations for large language models☆336Updated last year
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆412Updated 6 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆283Updated 2 years ago
- Benchmarking Complex Instruction-Following with Multiple Constraints Composition (NeurIPS 2024 Datasets and Benchmarks Track)☆99Updated 10 months ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆98Updated last year
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆162Updated 5 months ago
- make LLM easier to use☆59Updated 2 years ago
- ☆182Updated 2 years ago
- ☆147Updated last year
- [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.☆253Updated last year
- [EMNLP 2023] Lion: Adversarial Distillation of Proprietary Large Language Models☆212Updated last year
- ☆213Updated last year
- 基于DPO算法微调语言大模型，简单好上手。☆48Updated last year
- 代码大模型 预训练&微调&DPO 数据处理 业界处理pipeline sota☆48Updated last year
- 百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本☆49Updated 2 years ago
- LLM guided text clustering☆112Updated 2 years 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☆60Updated last year