Alternatives and similar repositories for hydra-moe:

Users that are interested in hydra-moe are comparing it to the libraries listed below

• epfml / landmark-attention
  Landmark Attention: Random-Access Infinite Context Length for Transformers
  ☆423Updated last year
• VikParuchuri / textbook_quality
  Generate textbook-quality synthetic LLM pretraining data
  ☆498Updated last year
• apoorvumang / prompt-lookup-decoding
  ☆524Updated 7 months ago
• jondurbin / bagel
  A bagel, with everything.
  ☆318Updated last year
• tomaarsen / attention_sinks
  Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
  ☆693Updated last year
• sabetAI / BLoRA
  batched loras
  ☆341Updated last year
• abacaj / train-with-fsdp
  ☆92Updated last year
• Gryphe / BlockMerge_Gradient
  Merge Transformers language models by use of gradient parameters.
  ☆206Updated 8 months ago
• imoneoi / multipack_sampler
  Multipack distributed sampler for fast padding-free training of LLMs
  ☆187Updated 8 months ago
• cognitivecomputations / laserRMT
  This is our own implementation of 'Layer Selective Rank Reduction'
  ☆234Updated 10 months ago
• hydrallm / llama-moe-v1
  ☆94Updated last year
• FastEval / FastEval
  Fast & more realistic evaluation of chat language models. Includes leaderboard.
  ☆186Updated last year
• persimmon-ai-labs / adept-inference
  Inference code for Persimmon-8B
  ☆415Updated last year
• jondurbin / airoboros
  Customizable implementation of the self-instruct paper.
  ☆1,042Updated last year
• abacaj / fine-tune-mistral
  Fine-tune mistral-7B on 3090s, a100s, h100s
  ☆709Updated last year
• Locutusque / TPU-Alignment
  Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free
  ☆231Updated 5 months ago
• IBM / ModuleFormer
  ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…
  ☆217Updated last year
• dzhulgakov / llama-mistral
  Inference code for Mistral and Mixtral hacked up into original Llama implementation
  ☆371Updated last year
• AblateIt / finetune-study
  Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.
  ☆82Updated last year
• abacusai / Long-Context
  This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and bench…
  ☆585Updated last year
• kmeng01 / memit
  Mass-editing thousands of facts into a transformer memory (ICLR 2023)
  ☆476Updated last year
• SqueezeAILab / SqueezeLLM
  [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
  ☆686Updated 8 months ago
• alasdairforsythe / tokenmonster
  Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript
  ☆577Updated 9 months ago
• eugenepentland / landmark-attention-qlora
  Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA
  ☆123Updated last year
• arielnlee / Platypus
  Code for fine-tuning Platypus fam LLMs using LoRA
  ☆629Updated last year
• Preemo-Inc / text-generation-inference
  ☆199Updated last year
• lm-sys / llm-decontaminator
  Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"
  ☆300Updated last year
• Cornell-RelaxML / QuIP
  Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
  ☆363Updated last year
• IST-DASLab / qmoe
  Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
  ☆273Updated last year
• HazyResearch / TART
  TART: A plug-and-play Transformer module for task-agnostic reasoning
  ☆196Updated last year