Saulp

Webshop-7B-RL-vllm

Saulp/Webshop-7B-RL-vllm

Webshop-7B-RL-vllm is a reinforcement learning model from Saulp. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

This repository is a standard Transformers export of Jianwen/Webshop-7B-RL. The source checkpoint stored the post-RL policy in FSDP actor shards; those shards were reconstructed without numerically mixing weights.