haizelabs / j1-microLinks
j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
☆98Updated 3 months ago
Alternatives and similar repositories for j1-micro
Users that are interested in j1-micro are comparing it to the libraries listed below
Sorting:
- ☆68Updated 5 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆58Updated this week
- A framework for optimizing DSPy programs with RL☆208Updated this week
- look how they massacred my boy☆63Updated last year
- Storing long contexts in tiny caches with self-study☆201Updated this week
- Super basic implementation (gist-like) of RLMs with REPL environments.☆132Updated last week
- Train your own SOTA deductive reasoning model☆108Updated 7 months ago
- ☆135Updated 7 months ago
- Simple GRPO scripts and configurations.☆59Updated 8 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆56Updated 5 months ago
- ☆40Updated last year
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆79Updated 7 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆71Updated 6 months ago
- ☆80Updated last week
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 9 months ago
- ⚖️ Awesome LLM Judges ⚖️☆132Updated 5 months ago
- smolLM with Entropix sampler on pytorch☆150Updated 11 months ago
- Training-Ready RL Environments + Evals☆128Updated this week
- Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles☆58Updated 5 months ago
- Project code for training LLMs to write better unit tests + code☆21Updated 5 months ago
- ☆49Updated 8 months ago
- ☆58Updated 8 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆24Updated this week
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated last year
- Small, simple agent task environments for training and evaluation☆18Updated 11 months ago
- Plotting (entropy, varentropy) for small LMs☆98Updated 5 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated 11 months ago
- PageRank for LLMs☆50Updated last month
- A DSPy-based implementation of the tree of thoughts method (Yao et al., 2023) for generating persuasive arguments☆89Updated 3 weeks ago
- XTR/WARP (SIGIR'25) is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.☆167Updated 5 months ago