MoFHeka / LLaMA-MegatronLinks
A LLaMA1/LLaMA12 Megatron implement.
☆28Updated last year
Alternatives and similar repositories for LLaMA-Megatron
Users that are interested in LLaMA-Megatron are comparing it to the libraries listed below
Sorting:
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆96Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆106Updated 3 months ago
- ☆84Updated last year
- Repository of LV-Eval Benchmark☆67Updated 9 months ago
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆40Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆114Updated 2 years ago
- Llama-3-SynE: A Significantly Enhanced Version of Llama-3 with Advanced Scientific Reasoning and Chinese Language Capabilities | 继续预训练提升 …☆33Updated 3 weeks ago
- ☆101Updated 8 months ago
- ☆63Updated 7 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆90Updated 2 months ago
- ☆105Updated 2 years 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
- NTK scaled version of ALiBi position encoding in Transformer.☆68Updated last year
- ACL 2024 | LooGLE: Long Context Evaluation for Long-Context Language Models☆185Updated 8 months ago
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆64Updated last year
- Multi-Candidate Speculative Decoding☆35Updated last year
- ☆141Updated 3 months ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆57Updated last year
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆154Updated last year
- Distributed IO-aware Attention algorithm☆20Updated 10 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆204Updated 6 months ago
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆221Updated last year
- ☆18Updated 2 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆384Updated last week
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 10 months ago
- ☆119Updated last year
- ☆77Updated 2 months ago
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆250Updated 6 months ago