Alternatives and similar repositories for pts

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

• tiiuae / onebitllms
  Lightweight toolkit package to train and fine-tune 1.58bit Language models
  ☆85Updated 3 months ago
• ritabratamaiti / AnyModal
  AnyModal is a Flexible Multimodal Language Model Framework for PyTorch
  ☆102Updated 8 months ago
• agokrani / distillKitPlus
  Easy to use, High Performant Knowledge Distillation for LLMs
  ☆92Updated 3 months ago
• neurallambda / awesome-reasoning
  a curated list of data for reasoning ai
  ☆137Updated last year
• mobiusml / aana_sdk
  Aana SDK is a powerful framework for building AI enabled multimodal applications.
  ☆52Updated last week
• LAION-AI / AIW
  Alice in Wonderland code base for experiments and raw experiments data
  ☆131Updated 3 weeks ago
• bradhilton / temporal-clue
  Clue inspired puzzles for testing LLM deduction abilities
  ☆40Updated 5 months ago
• egozverev / Should-It-Be-Executed-Or-Processed
  Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.
  ☆54Updated 5 months ago
• s-smits / grpo-optuna
  Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
  ☆55Updated 6 months ago
• Zyphra / transformers_zamba2
  ☆48Updated 6 months ago
• Mihaiii / backtrack_sampler
  An easy-to-understand framework for LLM samplers that rewind and revise generated tokens
  ☆146Updated 6 months ago
• lechmazur / nyt-connections
  Benchmark that evaluates LLMs using 651 NYT Connections puzzles extended with extra trick words
  ☆136Updated last week
• Columbia-NLP-Lab / PAPILLON
  Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles
  ☆54Updated 3 months ago
• reka-ai / rekaquant
  ☆60Updated last month
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆104Updated 5 months ago
• Danau5tin / terminal-bench-rl
  GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's T…
  ☆232Updated this week
• nahidalam / maya
  Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya
  ☆117Updated 3 weeks ago
• nexusflowai / NexusBench
  Nexusflow function call, tool use, and agent benchmarks.
  ☆29Updated 8 months ago
• shirley-wu / cot_decoding
  ☆45Updated last year
• ZhangYiqun018 / AvengersPro
  ☆134Updated this week
• haizelabs / j1-micro
  j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
  ☆95Updated last month
• cgftinc / benchmax
  Framework-Agnostic RL Environments for LLM Fine-Tuning
  ☆31Updated last week
• NolanoOrg / SpectraSuite
  ☆51Updated last year
• arcee-ai / DAM
  ☆54Updated 9 months ago
• QuixiAI / dolphin-logger
  ☆102Updated 2 months ago
• ArturTanona / grpo_unsloth_docker
  ☆57Updated 6 months ago
• llmonpy / needle-in-a-needlestack
  ☆116Updated 6 months ago
• XiaoduoAILab / XmodelLM
  XmodelLM
  ☆39Updated 9 months ago
• matthewrenze / jhu-concise-cot
  The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models
  ☆22Updated 9 months ago
• kubernetes-bad / reward-composer
  Lego for GRPO
  ☆29Updated 3 months ago