Alternatives and similar repositories for URM

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

• s-smits / grpo-optuna
  Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
  ☆59Updated 2 months ago
• RiddleHe / llm-interp
  A collection of lightweight interpretability scripts to understand how LLMs think
  ☆71Updated this week
• tyler-romero / microR1
  Simple repository for training small reasoning models
  ☆47Updated 10 months ago
• sunnweiwei / PPP-Agent
  ☆92Updated last month
• facebookresearch / llm-speedrunner
  The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…
  ☆121Updated 2 months ago
• arcee-ai / DAM
  ☆55Updated last year
• areu01or00 / Tensor-Slayer
  Tensor-Slayer : Manipulate weights and tensors of LLMs to achieve performance upgrades and introduce a novel inferenceless mechanistic in…
  ☆27Updated 6 months ago
• OpenEvaByte / evabyte
  EvaByte: Efficient Byte-level Language Models at Scale
  ☆111Updated 7 months ago
• kubernetes-bad / reward-composer
  Lego for GRPO
  ☆30Updated 6 months ago
• OpenMOSS / Lorsa
  ☆29Updated last month
• allenai / fluid-benchmarking
  Fluid Language Model Benchmarking
  ☆22Updated 3 months ago
• uq-project / UQ
  UQ: Assessing Language Models on Unsolved Questions
  ☆29Updated 3 months ago
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆107Updated 9 months ago
• anpaure / cp_eval
  Tiny evaluation of leading LLMs on competitive programming problems
  ☆14Updated last year
• kyegomez / OpenStrawberry
  An open source replication of the stawberry method that leverages Monte Carlo Search with PPO and or DPO
  ☆29Updated last week
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated last year
• dnakov / llm-asi-arch
  🤖 Complete reproduction of 'AlphaGo Moment for Model Architecture Discovery' using MLX-LM instead of GPT-4. Autonomous neural architectu…
  ☆26Updated 4 months ago
• goncalorafaria / qalign
  QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.
  ☆26Updated last week
• minosvasilias / simple_grpo
  Simple GRPO scripts and configurations.
  ☆59Updated 10 months ago
• gkamradt / SnakeBench
  ☆98Updated last week
• facebookresearch / ZeroSumEval
  A framework for pitting LLMs against each other in an evolving library of games ⚔
  ☆34Updated 8 months ago
• axolotl-ai-cloud / axolotl-cookbook
  ☆36Updated 4 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**.
  ☆63Updated 7 months ago
• okarthikb / state-space-models
  ☆28Updated last year
• HyperPotatoNeo / RSA
  ☆77Updated 2 months ago
• tinnerhrhe / ROVER
  An official implementation of Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
  ☆31Updated 2 months ago
• axolotl-ai-cloud / grpo_code
  A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.
  ☆40Updated 8 months ago
• lucidrains / mind-evolution
  Implementation of Mind Evolution, Evolving Deeper LLM Thinking, from Deepmind
  ☆57Updated 6 months ago
• VatsaDev / NanoPoor
  NanoGPT-speedrunning for the poor T4 enjoyers
  ☆73Updated 7 months ago
• reka-ai / rekaquant
  ☆62Updated 5 months ago