axolotl-ai-cloud / grpo_codeLinks
A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.
☆26Updated 2 months ago
Alternatives and similar repositories for grpo_code
Users that are interested in grpo_code are comparing it to the libraries listed below
Sorting:
- Simple GRPO scripts and configurations.☆58Updated 4 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 4 months ago
- ☆49Updated 7 months ago
- Verifiers for LLM Reinforcement Learning☆56Updated last month
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆90Updated 4 months ago
- Train your own SOTA deductive reasoning model☆93Updated 3 months ago
- ☆59Updated 2 weeks ago
- Simple repository for training small reasoning models☆31Updated 4 months ago
- entropix style sampling + GUI☆26Updated 7 months ago
- ☆41Updated 5 months ago
- Simple examples using Argilla tools to build AI☆53Updated 6 months ago
- ☆24Updated 8 months ago
- ☆43Updated 3 months ago
- Very minimal (and stateless) agent framework☆44Updated 4 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆67Updated 2 months ago
- Score LLM pretraining data with classifiers☆55Updated last year
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- ☆50Updated last week
- LLM reads a paper and produce a working prototype☆57Updated last month
- ☆11Updated 10 months ago
- ☆16Updated 3 months ago
- Lego for GRPO☆28Updated last week
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆38Updated last month
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- ☆58Updated 3 weeks ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 6 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆60Updated last week
- EMNLP 2024 "Re-reading improves reasoning in large language models". Simply repeating the question to get bidirectional understanding for…☆26Updated 5 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆57Updated 9 months ago
- Fine-tunes a student LLM using teacher feedback for improved reasoning and answer quality. Implements GRPO with teacher-provided evaluati…☆43Updated last month