Alternatives and similar repositories for unit_test_rl

Users that are interested in unit_test_rl 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 3 months ago
• brendanhogan / picoDeepResearch
  ☆67Updated 8 months ago
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated last year
• brendanhogan / completion_tree_view
  ☆15Updated 9 months ago
• minosvasilias / simple_grpo
  Simple GRPO scripts and configurations.
  ☆59Updated last year
• anpaure / cp_eval
  Tiny evaluation of leading LLMs on competitive programming problems
  ☆14Updated last year
• xjdr-alt / muzero_sketch
  ☆40Updated last year
• Pleias / Quest-Best-Tokens
  An introduction to LLM Sampling
  ☆79Updated last year
• catid / lllm
  Latent Large Language Models
  ☆19Updated last year
• joey00072 / Attention-as-graph
  alternative way to calculating self attention
  ☆18Updated last year
• huggingface / wikirace-llms
  ☆25Updated 9 months ago
• N8python / mlx-pretrain
  A simple MLX implementation for pretraining LLMs on Apple Silicon.
  ☆85Updated 5 months ago
• AnswerDotAI / ModernBERT-Instruct-mini-cookbook
  ☆53Updated last year
• SinatrasC / entropix
  Entropy Based Sampling and Parallel CoT Decoding
  ☆17Updated last year
• axolotl-ai-cloud / axolotl-cookbook
  ☆39Updated 6 months ago
• Alex-Gurung / ReasoningNCP
  Official repo for Learning to Reason for Long-Form Story Generation
  ☆74Updated 9 months ago
• axeld5 / pali_reason
  Testing paligemma2 finetuning on reasoning dataset
  ☆18Updated last year
• VatsaDev / NanoPoor
  NanoGPT-speedrunning for the poor T4 enjoyers
  ☆73Updated 9 months ago
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆107Updated 11 months ago
• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆110Updated 11 months ago
• haizelabs / j1-micro
  j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
  ☆102Updated 6 months ago
• JD-P / RetroInstruct
  Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.
  ☆32Updated 4 months ago
• enjalot / latent-data-modal
  Using modal.com to process FineWeb-edu data
  ☆20Updated 10 months ago
• JoshuaPurtell / SmallBench
  Small, simple agent task environments for training and evaluation
  ☆19Updated last year
• Xalp / ECHO
  Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)
  ☆92Updated last year
• matthewrenze / jhu-concise-cot
  The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models
  ☆24Updated last year
• smolorg / smoltropix
  MLX port for xjdr's entropix sampler (mimics jax implementation)
  ☆61Updated last year
• kurakurai / Luth
  Luth is a state-of-the-art series of fine-tuned LLMs for French
  ☆41Updated 3 months ago
• reka-ai / rekaquant
  ☆62Updated 7 months ago
• Osmosis-AI / Osmosis-Apply-1.7B-MCP
  A mcp server that uses the Osmosis-Apply-1.7B model to apply code merges
  ☆53Updated 7 months ago