Alternatives and similar repositories for RL

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

• VatsaDev / NanoPoor
  NanoGPT-speedrunning for the poor T4 enjoyers
  ☆73Updated 8 months ago
• RiddleHe / llm-interp
  A collection of lightweight interpretability scripts to understand how LLMs think
  ☆88Updated last week
• Pleias / Quest-Best-Tokens
  An introduction to LLM Sampling
  ☆79Updated last year
• N8python / mlx-pretrain
  A simple MLX implementation for pretraining LLMs on Apple Silicon.
  ☆85Updated 4 months ago
• tyler-romero / microR1
  Simple repository for training small reasoning models
  ☆47Updated 11 months ago
• xjdr-alt / simple_transformer
  Simple Transformer in Jax
  ☆140Updated last year
• kmohan321 / Research_Papers
  ☆46Updated 9 months ago
• saurabhaloneai / Llama-3-From-Scratch-In-Pure-Jax
  This repository contain the simple llama3 implementation in pure jax.
  ☆70Updated 10 months ago
• nano-R1 / resources
  Compiling useful links, papers, benchmarks, ideas, etc.
  ☆46Updated 9 months ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆286Updated 3 months ago
• brendanhogan / picoDeepResearch
  ☆68Updated 7 months ago
• naklecha / llm-inference-optimizations-explained
  in this repository, i'm going to implement increasingly complex llm inference optimizations
  ☆79Updated 7 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**.
  ☆65Updated 8 months ago
• Laz4rz / GPT-2
  Following Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish
  ☆172Updated last year
• SinatrasC / entropix-smollm
  smolLM with Entropix sampler on pytorch
  ☆149Updated last year
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated last year
• smolorg / smoltropix
  MLX port for xjdr's entropix sampler (mimics jax implementation)
  ☆61Updated last year
• attentionmech / tensorlens
  aesthetic tensor visualiser
  ☆28Updated 8 months ago
• haizelabs / j1-micro
  j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
  ☆100Updated 5 months ago
• okarthikb / state-space-models
  ☆27Updated last year
• usamec / lowmem_finetuning
  Low memory full parameter finetuning of LLMs
  ☆53Updated 5 months ago
• MekkCyber / TritonAcademy
  A repository to unravel the language of GPUs, making their kernel conversations easy to understand
  ☆195Updated 7 months ago
• jxmorris12 / embzip
  lossily compress representation vectors using product quantization
  ☆59Updated 2 months ago
• areu01or00 / Tensor-Slayer
  Tensor-Slayer : Manipulate weights and tensors of LLMs to achieve performance upgrades and introduce a novel inferenceless mechanistic in…
  ☆27Updated 7 months ago
• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆109Updated 10 months ago
• muellerzr / minimal-trainer-zoo
  Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines
  ☆196Updated last year
• sdan / vlm-gym
  RL gym for vision language models written in JAX
  ☆140Updated 2 months ago
• doomslide / hyperobject
  Plotting (entropy, varentropy) for small LMs
  ☆99Updated 7 months ago
• divyamakkar0 / JAXformer
  A zero-to-one guide on scaling modern transformers with n-dimensional parallelism.
  ☆112Updated 2 weeks ago
• NielsRogge / tutorials
  A repository containing general tutorials I'd like to share with the world.
  ☆80Updated last month