ModelHub XC 249dffd2aa 初始化项目,由ModelHub XC社区提供模型
Model: Huggggooo/ProtoCycle-7B-SFT
Source: Original Platform
2026-04-22 11:00:44 +08:00

license, library_name, pipeline_tag, base_model, tags, language
license library_name pipeline_tag base_model tags language
apache-2.0 transformers text-generation Qwen/Qwen2.5-7B-Instruct
protein-design
agentic
tool-use
qwen2.5
sft
en

ProtoCycle-7B-SFT

Cold-start SFT checkpoint for ProtoCycle — an agentic protein design model trained to invoke biology tools (scaffold retrieval, constraint building, ESM inpainting, ProTrek scoring) via a <think> / <plan> / <tool_call> / <answer> protocol.

This checkpoint is the SFT stage initialised from Qwen/Qwen2.5-7B-Instruct and is the starting point for the subsequent RL stage (Huggggooo/ProtoCycle-7B).

  • Base model: Qwen/Qwen2.5-7B-Instruct
  • Training framework: VeRL / Open-AgentRL
  • Stage: multi-turn SFT on agentic tool-use trajectories
  • Epochs: 5
  • Sequence length: 32k (with Ulysses SP=4)

Training Data

2,000 agentic multi-turn trajectories for protein design, available at Huggggooo/ProtoCycle-Data (sft/ subset).

How to Use

See the ProtoCycle repository: ProtoCycle repo.

Agent Protocol

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

Training Data

Agentic multi-turn trajectories for protein design (not released here).

License

Apache-2.0, consistent with the upstream VeRL / Open-AgentRL projects and the underlying Qwen2.5 license.

Citation

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

Description
Model synced from source: Huggggooo/ProtoCycle-7B-SFT
Readme 2 MiB
Languages
Jinja 100%