Edit model card

This is the official checkpoint of feedback model trained using COFFEE-GYM with PPO strategy.

This model generates natural language feedback given an erroneous code.

For further detials, please see our paper.

https://huggingface.co/spaces/Coffee-Gym/Project-Coffee-Gym

Downloads last month: 10

Safetensors

Model size

6.74B params

Tensor type

F32

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Team-Coffee-Gym/DS-Coder-7B-PPO-CoffeeEval

Quantizations

1 model

Team-Coffee-Gym
/

DS-Coder-7B-PPO-CoffeeEval

Model tree for Team-Coffee-Gym/DS-Coder-7B-PPO-CoffeeEval

Spaces using Team-Coffee-Gym/DS-Coder-7B-PPO-CoffeeEval 2