Alternatives and similar repositories for RLlama

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

• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆98Updated 2 months ago
• tyler-romero / microR1
  Simple repository for training small reasoning models
  ☆27Updated 3 months ago
• willccbb / trl
  Train transformer language models with reinforcement learning.
  ☆18Updated 2 months ago
• nano-R1 / resources
  Compiling useful links, papers, benchmarks, ideas, etc.
  ☆46Updated 2 months ago
• VatsaDev / NanoPoor
  NanoGPT-speedrunning for the poor T4 enjoyers
  ☆65Updated 3 weeks ago
• s-smits / grpo-optuna
  Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
  ☆53Updated 3 months ago
• okarthikb / state-space-models
  ☆27Updated 10 months ago
• kubernetes-bad / reward-composer
  Lego for GRPO
  ☆28Updated last month
• ivanleomk / modal-grpo
  ☆19Updated 2 months ago
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆65Updated last month
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆92Updated 2 months ago
• N8python / mlx-pretrain
  A simple MLX implementation for pretraining LLMs on Apple Silicon.
  ☆75Updated 2 weeks ago
• xjdr-alt / muzero_sketch
  ☆38Updated 9 months ago
• minosvasilias / simple_grpo
  Simple GRPO scripts and configurations.
  ☆58Updated 3 months ago
• andrew-silva / clean-rl-mlx
  Clean RL implementation using MLX
  ☆30Updated last year
• kmohan321 / Research_Papers
  ☆46Updated last month
• Danau5tin / calculator_agent_rl
  Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.
  ☆37Updated last week
• andrew-silva / mlx-rlhf
  An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.
  ☆26Updated 10 months ago
• saurabhaloneai / Llama-3-From-Scratch-In-Pure-Jax
  This repository contain the simple llama3 implementation in pure jax.
  ☆63Updated 2 months ago
• smolorg / smoltropix
  MLX port for xjdr's entropix sampler (mimics jax implementation)
  ☆64Updated 6 months ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆109Updated 3 weeks ago
• jerber / arc_agi
  ☆54Updated 3 months ago
• kabir2505 / tiny-mixtral
  ☆30Updated last week
• jxmorris12 / embzip
  lossily compress representation vectors using product quantization
  ☆53Updated 3 weeks ago
• TheProxyCompany / proxy-inference-engine
  Optimized LLM inference for Apple Silicon using MLX.
  ☆10Updated this week
• VectorInstitute / fed-rag
  A framework for fine-tuning retrieval-augmented generation (RAG) systems.
  ☆26Updated this week
• Pleias / Quest-Best-Tokens
  An introduction to LLM Sampling
  ☆78Updated 5 months ago
• PrimeIntellect-ai / genesys
  ☆125Updated last month
• google-deepmind / mishax
  ☆129Updated last month
• facebookresearch / ZeroSumEval
  A framework for pitting LLMs against each other in an evolving library of games ⚔
  ☆31Updated 3 weeks ago