Alternatives and similar repositories for RL

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

• N8python / mlx-pretrain
  A simple MLX implementation for pretraining LLMs on Apple Silicon.
  ☆83Updated 3 months ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆193Updated this week
• Pleias / Quest-Best-Tokens
  An introduction to LLM Sampling
  ☆79Updated 7 months ago
• smolorg / smoltropix
  MLX port for xjdr's entropix sampler (mimics jax implementation)
  ☆62Updated 9 months ago
• brendanhogan / picoDeepResearch
  ☆65Updated 2 months ago
• kmohan321 / Research_Papers
  ☆46Updated 4 months ago
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated 9 months ago
• haizelabs / j1-micro
  j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
  ☆95Updated 3 weeks ago
• naklecha / llm-inference-optimizations-explained
  in this repository, i'm going to implement increasingly complex llm inference optimizations
  ☆64Updated 2 months ago
• SinatrasC / entropix-smollm
  smolLM with Entropix sampler on pytorch
  ☆150Updated 9 months ago
• VatsaDev / NanoPoor
  NanoGPT-speedrunning for the poor T4 enjoyers
  ☆69Updated 3 months ago
• Laz4rz / GPT-2
  Following master Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish
  ☆172Updated last year
• nano-R1 / resources
  Compiling useful links, papers, benchmarks, ideas, etc.
  ☆45Updated 4 months ago
• YuvrajSingh-mist / Reinforcement-Learning
  ☆82Updated last week
• ariG23498 / gemma3-object-detection
  Fine tune Gemma 3 on an object detection task
  ☆74Updated 3 weeks ago
• SRSWTI / axis
  AI eXplainable Inference & Search. Open Sourcing on-premise, ultra-fast latency intelligence to all.
  ☆34Updated 5 months ago
• HarleyCoops / OneShotGRPO
  One click away from a locally downloaded, fine-tuned model, hosted on hugging face, with inference built in. In two hours.
  ☆22Updated 5 months ago
• Danau5tin / calculator_agent_rl
  Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.
  ☆45Updated 3 months ago
• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆104Updated 5 months ago
• jxmorris12 / embzip
  lossily compress representation vectors using product quantization
  ☆58Updated 3 months ago
• ManuelFay / Tutorials
  Quick Notebook Tutorials
  ☆36Updated 3 weeks ago
• xjdr-alt / simple_transformer
  Simple Transformer in Jax
  ☆138Updated last year
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆104Updated 5 months ago
• PrimeIntellect-ai / pi-quant
  SIMD quantization kernels
  ☆78Updated last week
• tom-pollak / claudette-pydantic
  ☆9Updated 9 months ago
• AI-Hypercomputer / RecML
  ☆186Updated this week
• taylorai / mlx_embedding_models
  run embeddings in MLX
  ☆90Updated 10 months ago
• smolorg / smolvecstore
  a tiny vectorstore implementation built with numpy.
  ☆63Updated last year
• usamec / lowmem_finetuning
  Low memory full parameter finetuning of LLMs
  ☆52Updated 3 weeks ago
• muellerzr / minimal-trainer-zoo
  Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines
  ☆197Updated last year