Alternatives and similar repositories for hackathon

Users that are interested in hackathon are comparing it to the libraries listed below

• MDK8888 / GPTFast
  Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.
  ☆687Updated last year
• Locutusque / TPU-Alignment
  Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free
  ☆232Updated 11 months ago
• mistralai / mistral-common
  Official inference library for pre-processing of Mistral models
  ☆794Updated last week
• mlabonne / llm-autoeval
  Automatically evaluate your LLMs in Google Colab
  ☆661Updated last year
• abacaj / fine-tune-mistral
  Fine-tune mistral-7B on 3090s, a100s, h100s
  ☆717Updated last year
• huggingface / optimum-nvidia
  ☆1,004Updated 8 months ago
• mistralai / megablocks-public
  ☆866Updated last year
• center-for-humans-and-machines / transformer-heads
  Toolkit for attaching, training, saving and loading of new heads for transformer models
  ☆289Updated 7 months ago
• lamini-ai / Lamini-Memory-Tuning
  Banishing LLM Hallucinations Requires Rethinking Generalization
  ☆276Updated last year
• migtissera / Sensei
  Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI
  ☆222Updated last year
• jondurbin / bagel
  A bagel, with everything.
  ☆325Updated last year
• myshell-ai / JetMoE
  Reaching LLaMA2 Performance with 0.1M Dollars
  ☆986Updated last year
• QuixiAI / laserRMT
  This is our own implementation of 'Layer Selective Rank Reduction'
  ☆240Updated last year
• tomaarsen / attention_sinks
  Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
  ☆720Updated last year
• taylorai / galactic
  data cleaning and curation for unstructured text
  ☆328Updated last year
• microsoft / Samba
  [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
  ☆912Updated 5 months ago
• AnswerDotAI / fsdp_qlora
  Training LLMs with QLoRA + FSDP
  ☆1,529Updated 10 months ago
• allenai / fm-cheatsheet
  Website for hosting the Open Foundation Models Cheat Sheet.
  ☆268Updated 4 months ago
• SkunkworksAI / hydra-moe
  ☆416Updated last year
• VikParuchuri / textbook_quality
  Generate textbook-quality synthetic LLM pretraining data
  ☆505Updated last year
• gavi / mlx-whatsapp
  An mlx project to train a base model on your whatsapp chats using (Q)Lora finetuning
  ☆170Updated last year
• nomic-ai / contrastors
  Train Models Contrastively in Pytorch
  ☆750Updated 6 months ago
• pbelcak / UltraFastBERT
  The repository for the code of the UltraFastBERT paper
  ☆519Updated last year
• deep-diver / llamaduo
  [ACL'25] Official Code for LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs
  ☆314Updated 2 months ago
• gautierdag / bpeasy
  Fast bare-bones BPE for modern tokenizer training
  ☆165Updated 3 months ago
• persimmon-ai-labs / adept-inference
  Inference code for Persimmon-8B
  ☆414Updated 2 years ago
• modal-labs / llm-finetuning
  Guide for fine-tuning Llama/Mistral/CodeLlama models and more
  ☆625Updated 4 months ago
• valine / NeuralFlow
  Visualize the intermediate output of Mistral 7B
  ☆371Updated 8 months ago
• apoorvumang / prompt-lookup-decoding
  ☆570Updated last year
• tigerlab-ai / tiger
  Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)
  ☆399Updated last year