Alternatives and similar repositories for vlm-gym

Users that are interested in vlm-gym 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)
  ☆108Updated 9 months ago
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated last year
• tensoic / Cerule
  Cerule - A Tiny Mighty Vision Model
  ☆68Updated 3 weeks ago
• s-smits / grpo-optuna
  Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
  ☆59Updated last month
• brendanhogan / picoDeepResearch
  ☆68Updated 6 months ago
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆107Updated 9 months ago
• doomslide / hyperobject
  Plotting (entropy, varentropy) for small LMs
  ☆99Updated 6 months ago
• willccbb / localchat
  ☆14Updated 7 months ago
• samefarrar / entropix_mlx
  Modify Entropy Based Sampling to work with Mac Silicon via MLX
  ☆49Updated last year
• kubernetes-bad / reward-composer
  Lego for GRPO
  ☆30Updated 6 months ago
• smolorg / smoltropix
  MLX port for xjdr's entropix sampler (mimics jax implementation)
  ☆62Updated last year
• ai8hyf / OpenResearchAssistant
  An automated tool for discovering insights from research papaer corpora
  ☆137Updated last year
• xjdr-alt / muzero_sketch
  ☆40Updated last year
• thesephist / spectre
  Sparse autoencoders for Contra text embedding models
  ☆25Updated last year
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆173Updated 10 months ago
• N8python / mlx-pretrain
  A simple MLX implementation for pretraining LLMs on Apple Silicon.
  ☆84Updated 3 months ago
• leloykun / modded-nanogpt
  NanoGPT (124M) quality in 2.67B tokens
  ☆28Updated 2 months ago
• PrimeIntellect-ai / prime-environments
  Training-Ready RL Environments + Evals
  ☆185Updated this week
• HazyResearch / cartridges
  Storing long contexts in tiny caches with self-study
  ☆218Updated 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…
  ☆112Updated last month
• goodfire-ai / sdxl-turbo-interpretability
  ☆47Updated 6 months ago
• SinatrasC / entropix-smollm
  smolLM with Entropix sampler on pytorch
  ☆149Updated last year
• Nearcyan / papers.day
  papers.day
  ☆91Updated last year
• matttreed / diloco-sim
  ☆21Updated 11 months ago
• xjdr-alt / simple_transformer
  Simple Transformer in Jax
  ☆139Updated last year
• PrimeIntellect-ai / pi-quant
  SIMD quantization kernels
  ☆93Updated 3 months ago
• JD-P / RetroInstruct
  Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.
  ☆32Updated last month
• haizelabs / j1-micro
  j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
  ☆99Updated 4 months ago
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆85Updated 7 months ago
• axolotl-ai-cloud / axolotl-cookbook
  ☆36Updated 4 months ago