genggui001 / Megatron-DeepSpeed-Llama
☆84Updated last year
Alternatives and similar repositories for Megatron-DeepSpeed-Llama:
Users that are interested in Megatron-DeepSpeed-Llama are comparing it to the libraries listed below
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆92Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆112Updated last year
- 怎么训练一个LLM分词器☆140Updated last year
- ☆162Updated last year
- 百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本☆47Updated last year
- 中文 Instruction tuning datasets☆126Updated 10 months ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆74Updated 3 months ago
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆215Updated last year
- A LLaMA1/LLaMA12 Megatron implement.☆28Updated last year
- NTK scaled version of ALiBi position encoding in Transformer.☆67Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆38Updated 11 months ago
- 文本去重☆68Updated 8 months ago
- ☆130Updated 10 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆70Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆19Updated last year
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆64Updated last year
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆118Updated 8 months ago
- ☆52Updated last year
- 大语言模型指令调优工具（支持 FlashAttention）☆169Updated last year
- ☆159Updated last year
- 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☆53Updated last year
- Model Compression for Big Models☆157Updated last year
- A more efficient GLM implementation!☆55Updated 2 years ago
- “悟道”数据☆41Updated 3 years ago
- 中文图书语料MD5链接☆213Updated last year
- deepspeed+trainer简单高效实现多卡微调大模型☆122Updated last year
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆56Updated 10 months ago
- ☆62Updated last year
- ☆45Updated 8 months ago