CoinCheung / gdGPT
Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
☆95Updated last year
Alternatives and similar repositories for gdGPT:
Users that are interested in gdGPT are comparing it to the libraries listed below
- 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
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- ☆84Updated last year
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆216Updated last year
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆153Updated 9 months ago
- ☆98Updated 6 months ago
- Repository of LV-Eval Benchmark☆61Updated 7 months ago
- A LLaMA1/LLaMA12 Megatron implement.☆28Updated last year
- A flexible and efficient training framework for large-scale alignment tasks☆333Updated last month
- ☆78Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆40Updated last year
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆91Updated last year
- code for Scaling Laws of RoPE-based Extrapolation☆72Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆177Updated last month
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆61Updated last year
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆247Updated 3 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆90Updated 2 weeks ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆115Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆67Updated 3 weeks ago
- Transformer related optimization, including BERT, GPT☆59Updated last year
- ☆128Updated 3 weeks ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆198Updated 4 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆313Updated 6 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆463Updated 2 weeks ago
- [ICML'24] The official implementation of “Rethinking Optimization and Architecture for Tiny Language Models”☆121Updated 2 months ago
- [ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)☆117Updated last month
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆247Updated last year
- ☆104Updated last year
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆207Updated 7 months ago
- Rectified Rotary Position Embeddings☆362Updated 10 months ago