---
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
base_model: Huggggooo/ProtoCycle-7B-SFT
tags:
  - protein-design
  - agentic
  - tool-use
  - qwen2.5
  - reinforcement-learning
  - grpo
language:
  - en
---

# ProtoCycle-7B

RL checkpoint for **ProtoCycle** — an agentic protein design model that
performs multi-step, tool-augmented sequence design.

This is the **GRPO-TCR (Group Relative Policy Optimization with Tool-Call
Reward) stage**, initialised from the SFT checkpoint
[`Huggggooo/ProtoCycle-7B-SFT`](https://huggingface.co/Huggggooo/ProtoCycle-7B-SFT).

- Base model: `Huggggooo/ProtoCycle-7B-SFT`
  (itself fine-tuned from `Qwen/Qwen2.5-7B-Instruct`)
- Training framework: [VeRL](https://github.com/volcengine/verl) /
  [Open-AgentRL](https://github.com/Gen-Verse/Open-AgentRL)
- Stage: agentic RL with GRPO-TCR
- Rollouts per prompt: 8, max turns: 16
- Max prompt / response: 8k / 20k tokens
- Reward manager: `protein` (see
  [ProtoCycle/verl/workers/reward_manager/protein.py](https://github.com/huggggoooooo/ProtoCycle/blob/main/verl/workers/reward_manager/protein.py))


See
[`recipe/protein/reward.py`](https://github.com/huggggoooooo/ProtoCycle/blob/main/recipe/protein/reward.py)
for the exact formulation.

## Training Data

10,000 RL prompts for GRPO-TCR training, available at
[Huggggooo/ProtoCycle-Data](https://huggingface.co/datasets/Huggggooo/ProtoCycle-Data) (`rl/` subset).}

## Agent Protocol

```
<think>  ... reasoning ...  </think>
<plan>   ... stage plan ...  </plan>
<tool_call>{"name": "...", "arguments": {...}}</tool_call>
...
<answer>MAEGEITPLKTF...</answer>
```

## How to Use

See the ProtoCycle repository: 
[ProtoCycle](https://github.com/huggggoooooo/ProtoCycle) repo.


## License

Apache-2.0.

## Citation

If you find this work useful, please cite ProtoCycle (forthcoming) and the
upstream frameworks: VeRL, Open-AgentRL, ProTrek, ESM.