Al-th / grpo_experimentLinks
Experiment on reimplementation of GRPO RL
☆13Updated 5 months ago
Alternatives and similar repositories for grpo_experiment
Users that are interested in grpo_experiment are comparing it to the libraries listed below
Sorting:
- Framework for specifying and proving properties—such as robustness, fairness, and interpretability—of machine learning models using Lean …☆63Updated last week
- Copies of prolog solvers for use from python☆18Updated last year
- A star for organising blocks and playing with transformers.☆23Updated last year
- ☆64Updated last month
- Rewriting Principia Mathematica in Lean☆132Updated 8 months ago
- Analyzing hacker news in real-time with Bytewax and Proton☆39Updated last year
- Visualize text embeddings☆40Updated 2 years ago
- A tiny autograd engine with a Jax-like API☆71Updated 2 weeks ago
- Advanced Python Function Debugging with MCP Integration.☆57Updated last month
- A multithreaded async event loop for python☆58Updated 9 months ago
- A GPU Accelerated Binary Vector Store☆47Updated 5 months ago
- A Full Transcript of the Lighthill Debate on AI from 1973, with Introductory Remarks☆31Updated last year
- PILF: A IPWT-inspired bionic continual learning experiment focus on mitigate catastrophic forgetting with Surprise-gated Mixture of Exper…☆33Updated last week
- A MCP server for symbolic manipulation of mathematical expressions☆34Updated 3 weeks ago
- Sequential Logic☆111Updated last week
- Extremely memory-efficient vector database☆71Updated 10 months ago
- Some experiments on transformer models☆11Updated last year
- PostgreSQL Prolog language handler☆134Updated last year
- Hierarchical topic segmentation of meeting transcripts using embeddings and divisive clustering.☆53Updated 11 months ago
- Lamport's Bakery Algorithm Demonstrated in Python☆96Updated last year
- Autoregressive transformers in APL☆102Updated 2 months ago
- Designing bridge trusses with Pytorch autograd☆61Updated last year
- ☆51Updated last year
- An easily-trained baby GPT that can stand in for the real thing. Based on Andrej Karpathy's makemore, but set up to mimic a llama-cpp ser…☆28Updated last year
- a categorical deep learning compiler☆203Updated 4 months ago
- ☆27Updated 10 months ago
- A playground to make it easy to try crazy things☆33Updated last month
- Dead Simple LLM Abliteration☆224Updated 5 months ago
- Learn multi-variable optimization by creating a drawing assistant. No deep learning required!☆28Updated 2 years ago
- Tools for LLM agents.☆63Updated 7 months ago