HuangLK / transpeederLinks
train llama on a single A100 80G node using π€βtransformers and πβDeepspeed Pipeline Parallelism
β224Updated last year
Alternatives and similar repositories for transpeeder
Users that are interested in transpeeder are comparing it to the libraries listed below
Sorting:
- β84Updated 2 years ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.β98Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chatβ114Updated 2 years ago
- Collaborative Training of Large Language Models in an Efficient Wayβ416Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2β69Updated 2 years ago
- Naive Bayes-based Context Extensionβ325Updated 9 months ago
- Rectified Rotary Position Embeddingsβ381Updated last year
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.β67Updated 2 years ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuningβ275Updated 2 years ago
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarksβ268Updated last year
- Model Compression for Big Modelsβ165Updated 2 years ago
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMsβ256Updated 9 months ago
- Code used for sourcing and cleaning the BigScience ROOTS corpusβ314Updated 2 years ago
- β460Updated last year
- NTK scaled version of ALiBi position encoding in Transformer.β69Updated 2 years ago
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Modelsβ42Updated last year
- A unified tokenization tool for Images, Chinese and English.β151Updated 2 years ago
- β176Updated last year
- β281Updated last year
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuningβ400Updated last year
- The aim of this repository is to utilize LLaMA to reproduce and enhance the Stanford Alpacaβ98Updated 2 years ago
- Efficient, Low-Resource, Distributed transformer implementation based on BMTrainβ262Updated last year
- β172Updated 2 years ago
- π An unofficial implementation of Self-Alignment with Instruction Backtranslation.β139Updated 4 months ago
- β105Updated 2 years ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimationβ89Updated 10 months ago
- A Multi-Turn Dialogue Corpus based on Alpaca Instructionsβ173Updated 2 years ago
- A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free toβ¦β57Updated 2 years ago
- code for Scaling Laws of RoPE-based Extrapolationβ73Updated last year
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasetsβ341Updated last year