Alternatives and similar repositories for reasoning-diffusion

Users that are interested in reasoning-diffusion are comparing it to the libraries listed below

• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆175Updated last year
• SinatrasC / entropix
  Entropy Based Sampling and Parallel CoT Decoding
  ☆17Updated last year
• arcprize / ARC-AGI-3-Agents
  ☆123Updated last week
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆170Updated 9 months ago
• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆110Updated 11 months ago
• facebookresearch / llm-speedrunner
  The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…
  ☆128Updated 4 months ago
• tanaymeh / mamba-train
  A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIM
  ☆61Updated last year
• PrimeIntellect-ai / genesys
  ☆137Updated 10 months ago
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated last year
• VsonicV / es-fine-tuning-paper
  This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"
  ☆292Updated 2 months ago
• ahstat / episodic-memory-benchmark
  Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…
  ☆63Updated 4 months ago
• brendanhogan / picoDeepResearch
  ☆67Updated 8 months ago
• SinatrasC / entropix-smollm
  smolLM with Entropix sampler on pytorch
  ☆149Updated last year
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆90Updated 10 months ago
• letta-ai / sleep-time-compute
  accompanying material for sleep-time compute paper
  ☆119Updated 9 months ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆286Updated 4 months ago
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆85Updated 3 weeks ago
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆107Updated 11 months ago
• Think-a-Tron / evolve
  open source alpha evolve
  ☆69Updated 8 months ago
• vicksEmmanuel / latent-gemma
  ☆26Updated last year
• s-smits / grpo-optuna
  Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
  ☆59Updated 3 months ago
• OpenEvaByte / evabyte
  EvaByte: Efficient Byte-level Language Models at Scale
  ☆115Updated 9 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 9 months ago
• sdan / vlm-gym
  RL gym for vision language models written in JAX
  ☆145Updated 3 months ago
• nano-R1 / resources
  Compiling useful links, papers, benchmarks, ideas, etc.
  ☆46Updated 10 months ago
• gkamradt / SnakeBench
  ☆100Updated last week
• HarleyCoops / smolThinker-.5B
  A Qwen .5B reasoning model trained on OpenR1-Math-220k
  ☆14Updated 3 months ago
• janhq / visual-thinker
  ☆182Updated 2 months ago
• RiddleHe / llm-interp
  A collection of lightweight interpretability scripts to understand how LLMs think
  ☆89Updated 2 weeks ago
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆251Updated 5 months ago