License: ProGen2 is open source and free for academic and commercial use under a BSD-3-Clause license. Please refer to the license 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.
evo-design/proto-language/proto_language/generator/progen2_generator.pyGenerator contributors
dguo8412
Protein sequence generator using ProGen2 autoregressive language model.
dguo8412API Reference
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/
For detailed information on ProGen2, see:
- HuggingFace: https://huggingface.co/hugohrban/
- GitHub: https://github.com/hugohrban/ProGen2-finetuning
- Original GitHub: https://github.com/enijkamp/progen2
- Original paper: https://www.cell.com/cell-systems/fulltext/S2405-4712(23)00272-7
List[string]
required
Prompt sequences for protein sequence generation
enum
default:"progen2-large"
ProGen2 model variant to load (e.g. progen2-large).Options:
progen2-small, progen2-medium, progen2-base, progen2-oas, progen2-large, progen2-BFD90, progen2-xlargestring
Path to local model weights
string
default:"cuda"
GPU device to run ProGen2 on (e.g. ‘cuda’ or ‘cuda:0’).
number
default:"0.2"
Sharpness of sampling. Below 1 favors high-probability tokens; above 1 increases diversity.
number
default:"0.95"
Nucleus sampling cumulative probability cutoff. 1.0 disables nucleus sampling.
integer
default:"0"
At each step, restrict sampling to the k most probable tokens. Set to 0 to disable top-k truncation.
boolean
default:"True"
Whether to truncate sequences at stop tokens
boolean
default:"True"
Whether to strip start and stop tokens from final output
boolean
default:"True"
Whether to prepend prompt to generation
integer
default:"1"
Number of sequences to process simultaneously on GPU
boolean
default:"False"
Whether to print verbose output
Usage
python