CoinCheung / gdGPT
Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
☆93Updated 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
- ☆84Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- Repository of LV-Eval Benchmark☆58Updated 6 months ago
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆215Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆166Updated 2 weeks ago
- A flexible and efficient training framework for large-scale alignment tasks☆311Updated 2 weeks ago
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆153Updated 8 months ago
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆61Updated last year
- ☆96Updated 5 months ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆112Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆39Updated 11 months ago
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆47Updated this week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆85Updated 4 months ago
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks☆256Updated 7 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆93Updated 9 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆230Updated this week
- A LLaMA1/LLaMA12 Megatron implement.☆28Updated last year
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆90Updated last year
- code for Scaling Laws of RoPE-based Extrapolation☆70Updated last year
- ☆58Updated 3 months ago
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆241Updated 2 months ago
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆143Updated 5 months ago
- [ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)☆110Updated 2 weeks ago
- ☆105Updated last year
- [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.☆233Updated 4 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆310Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆98Updated 2 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆242Updated last year
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆206Updated 6 months ago