MoFHeka / LLaMA-Megatron
A LLaMA1/LLaMA12 Megatron implement.
☆26Updated 9 months ago
Related projects: ⓘ
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆90Updated 7 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆67Updated last year
- ☆82Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆37Updated 6 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting☆60Updated 6 months ago
- ☆105Updated last week
- ☆60Updated last month
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆133Updated 3 months ago
- Repository of LV-Eval Benchmark☆41Updated 3 weeks ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆106Updated last year
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆101Updated 2 weeks ago
- Distributed IO-aware Attention algorithm☆17Updated 3 weeks ago
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆56Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆158Updated 4 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆183Updated last month
- A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to…☆45Updated last year
- ☆87Updated 4 months ago
- Transformer related optimization, including BERT, GPT☆58Updated last year
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆61Updated 4 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆68Updated 11 months ago
- NTK scaled version of ALiBi position encoding in Transformer.☆64Updated last year
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆244Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆57Updated 2 months ago
- Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment☆60Updated 3 months ago
- ☆99Updated last year
- An Experiment on Dynamic NTK Scaling RoPE☆59Updated 9 months ago
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆72Updated 6 months ago
- Multi-Candidate Speculative Decoding☆27Updated 4 months ago
- ☆32Updated 3 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆78Updated 4 months ago