HuangLK / transpeeder
train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism
☆219Updated last year
Alternatives and similar repositories for transpeeder:
Users that are interested in transpeeder are comparing it to the libraries listed below
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆115Updated last year
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆95Updated last year
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆395Updated 11 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆256Updated last year
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆249Updated 4 months ago
- Naive Bayes-based Context Extension☆326Updated 4 months ago
- ☆459Updated 10 months ago
- Collaborative Training of Large Language Models in an Efficient Way☆415Updated 8 months ago
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆363Updated 8 months ago
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks☆260Updated 9 months ago
- Code used for sourcing and cleaning the BigScience ROOTS corpus☆311Updated 2 years ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆323Updated 7 months ago
- Rectified Rotary Position Embeddings☆367Updated 11 months ago
- ☆84Updated last year
- A Multi-Turn Dialogue Corpus based on Alpaca Instructions☆170Updated last year
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆459Updated last year
- [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.☆240Updated 6 months ago
- A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to…☆55Updated last year
- LongQLoRA: Extent Context Length of LLMs Efficiently☆164Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- ☆280Updated last year
- [ACL'24 Outstanding] Data and code for L-Eval, a comprehensive long context language models evaluation benchmark☆376Updated 9 months ago
- A unified tokenization tool for Images, Chinese and English.☆152Updated 2 years ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆553Updated 4 months ago
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆40Updated last year
- A flexible and efficient training framework for large-scale alignment tasks☆343Updated 2 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- The aim of this repository is to utilize LLaMA to reproduce and enhance the Stanford Alpaca☆97Updated 2 years ago
- 🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.☆139Updated 10 months ago
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆149Updated 8 months ago