alibaba / Megatron-LLaMALinks
Best practice for training LLaMA models in Megatron-LM
☆659Updated last year
Alternatives and similar repositories for Megatron-LLaMA
Users that are interested in Megatron-LLaMA are comparing it to the libraries listed below
Sorting:
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,418Updated last week
- A flexible and efficient training framework for large-scale alignment tasks☆437Updated 3 weeks ago
- Efficient Training (including pre-training and fine-tuning) for Big Models☆613Updated 2 weeks ago
- Collaborative Training of Large Language Models in an Efficient Way☆414Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,427Updated last year
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆995Updated 11 months ago
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆225Updated last year
- Fast inference from large lauguage models via speculative decoding☆848Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,188Updated 2 months ago
- Accelerate inference without tears☆365Updated 3 weeks ago
- LongBench v2 and LongBench (ACL 25'&24')☆1,008Updated 9 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆404Updated this week
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks☆268Updated last year
- ☆321Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆591Updated 3 weeks ago
- Ring attention implementation with flash attention☆906Updated 2 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆920Updated this week
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆98Updated last year
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆407Updated 3 months ago
- Rectified Rotary Position Embeddings☆381Updated last year
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆411Updated 2 months ago
- ☆84Updated 2 years ago
- ☆459Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆631Updated last year
- Model Compression for Big Models☆165Updated 2 years ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,297Updated 8 months ago
- Naive Bayes-based Context Extension☆324Updated 11 months ago
- Microsoft Automatic Mixed Precision Library☆627Updated last year
- ☆176Updated this week
- Code used for sourcing and cleaning the BigScience ROOTS corpus☆316Updated 2 years ago