minosvasilias / simple_grpoLinks
Simple GRPO scripts and configurations.
☆59Updated 7 months ago
Alternatives and similar repositories for simple_grpo
Users that are interested in simple_grpo are comparing it to the libraries listed below
Sorting:
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 8 months ago
- ☆54Updated 10 months ago
- ☆49Updated 7 months ago
- ☆40Updated last year
- ☆88Updated last year
- Project code for training LLMs to write better unit tests + code☆21Updated 4 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 7 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆72Updated 5 months ago
- Simple repository for training small reasoning models☆40Updated 7 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- An introduction to LLM Sampling☆79Updated 9 months ago
- Train your own SOTA deductive reasoning model☆107Updated 6 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆53Updated 5 months ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆56Updated this week
- ☆48Updated last year
- ☆39Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆34Updated last year
- LLM training in simple, raw C/CUDA☆15Updated 10 months ago
- look how they massacred my boy☆63Updated 11 months ago
- ☆58Updated 4 months ago
- Verifiers for LLM Reinforcement Learning☆74Updated 5 months ago
- smolLM with Entropix sampler on pytorch☆150Updated 11 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆59Updated last year
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆27Updated 4 months ago
- Latent Large Language Models☆19Updated last year
- A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.☆38Updated 6 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆98Updated 2 months ago
- ☆101Updated 8 months ago
- ☆35Updated 2 months ago
- Mixing Language Models with Self-Verification and Meta-Verification☆110Updated 9 months ago