SinatrasC / entropixLinks
Entropy Based Sampling and Parallel CoT Decoding
☆17Updated 11 months ago
Alternatives and similar repositories for entropix
Users that are interested in entropix are comparing it to the libraries listed below
Sorting:
- look how they massacred my boy☆63Updated 11 months ago
- ☆133Updated 6 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆77Updated 6 months ago
- train entropix like a champ!☆20Updated 11 months ago
- ☆68Updated 4 months ago
- Plotting (entropy, varentropy) for small LMs☆99Updated 4 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆72Updated 5 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 7 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- entropix style sampling + GUI☆27Updated 11 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 6 months ago
- smolLM with Entropix sampler on pytorch☆150Updated 11 months ago
- Train your own SOTA deductive reasoning model☆107Updated 6 months ago
- working implimention of deepseek MLA☆44Updated 8 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated 10 months ago
- ☆135Updated last year
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated 10 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆109Updated 5 months ago
- Project code for training LLMs to write better unit tests + code☆21Updated 4 months ago
- ☆13Updated 5 months ago
- Simple GRPO scripts and configurations.☆59Updated 7 months ago
- ☆40Updated last year
- A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.☆38Updated 5 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆52Updated 4 months ago
- ☆54Updated 10 months ago
- ☆123Updated 7 months ago
- A Qwen .5B reasoning model trained on OpenR1-Math-220k☆14Updated 7 months ago
- Marketplace ML experiment - training without backprop☆25Updated 3 weeks ago
- An introduction to LLM Sampling☆79Updated 9 months ago
- Lego for GRPO☆29Updated 4 months ago