> ## Documentation Index > Fetch the complete documentation index at: https://proto.evodesign.org/docs/llms.txt > Use this file to discover all available pages before exploring further. # ProGen2 Protein Language Model > ProGen2 autoregressive protein language model for protein sequence generation
ProGen2 Protein Language Model
**License:** ProGen2 is open source and free for academic and commercial use under a BSD-3-Clause license. Please refer to [the license](https://github.com/enijkamp/progen2/blob/main/LICENSE.txt) for full terms.

This generator is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.

Go to Tool Page
evo-design/proto-language/proto\_language/generator/progen2\_generator.py
View source
```bibtex theme={null} @article{nijkamp2023progen2, title={ProGen2: Exploring the boundaries of protein language models}, author={Nijkamp, Erik and Ruffolo, Jeffrey A and Weinstein, Eli N and Naik, Nikhil and Madani, Ali}, journal={Cell Systems}, volume={14}, number={11}, pages={968--978}, year={2023}, publisher={Elsevier}, doi={10.1016/j.cels.2023.10.002} } ```
Copy citation
Generator contributors
Protein sequence generator using ProGen2 autoregressive language model. ## API Reference
ConfigProGen2GeneratorConfig Source
Configuration object for ProGen2Generator. This class defines configuration parameters for the ProGen2 generator, which uses the ProGen2 protein language model to autoregressively generate protein sequences from prompt sequences. Models are loaded from HuggingFace: [https://huggingface.co/hugohrban/](https://huggingface.co/hugohrban/) For detailed information on ProGen2, see: * HuggingFace: [https://huggingface.co/hugohrban/](https://huggingface.co/hugohrban/) * GitHub: [https://github.com/hugohrban/ProGen2-finetuning](https://github.com/hugohrban/ProGen2-finetuning) * Original GitHub: [https://github.com/enijkamp/progen2](https://github.com/enijkamp/progen2) * Original paper: [https://www.cell.com/cell-systems/fulltext/S2405-4712(23)00272-7](https://www.cell.com/cell-systems/fulltext/S2405-4712\(23\)00272-7) Prompt sequences for protein sequence generation ProGen2 model variant to load (e.g. progen2-large). Options: `progen2-small`, `progen2-medium`, `progen2-base`, `progen2-oas`, `progen2-large`, `progen2-BFD90`, `progen2-xlarge` Path to local model weights GPU device to run ProGen2 on (e.g. 'cuda' or 'cuda:0'). Sharpness of sampling. Below 1 favors high-probability tokens; above 1 increases diversity. Nucleus sampling cumulative probability cutoff. 1.0 disables nucleus sampling. At each step, restrict sampling to the k most probable tokens. Set to 0 to disable top-k truncation. Whether to truncate sequences at stop tokens Whether to strip start and stop tokens from final output Whether to prepend prompt to generation Number of sequences to process simultaneously on GPU Whether to print verbose output
## Usage ```python python icon="python" theme={null} from proto_language.generator import ProGen2Generator, ProGen2GeneratorConfig from proto_language.core import Segment config = ProGen2GeneratorConfig( # Configure parameters here ) generator = ProGen2Generator(config) segment = Segment(length=100, sequence_type="protein") generator.assign(segment) generator.sample() ``` ## Metadata | Property | Value | | ------------------------ | ------------------ | | Key | `progen2` | | Class | `ProGen2Generator` | | Category | `autoregressive` | | Input Type | `prompt` | | Uses GPU | `True` | | Supported Sequence Types | `protein` | | Allows Empty Start | `False` |