InstructPro2 is an open-weight model from Charles Novak, released under MIT License. Its published files total 24.2 GB.
Model weights for InstructPro2: Natural Language and Biological Grounding Guided De Novo Protein Design — a 3.2B protein design model that generates sequences from natural-language function descriptions, optionally conditioned on a ligand or an antigen.
Model Card
By Charles Novak, published under mit, revision a804b80e49cb.
Model weights for InstructPro2: Natural Language and Biological Grounding Guided De Novo Protein Design — a 3.2B protein design model that generates sequences from natural-language function descriptions, optionally conditioned on a ligand or an antigen. The Stage 2 checkpoints are larger because they carry the gated cross-attention adapters and the frozen ChemBERTa and ESM-2 encoders. Pass a checkpoint to the scripts in the code repository: The scripts set the architecture mode and the generation settings for each checkpoint; see the code repository's README.
Read Charles Novak's full model card
Model weights for InstructPro2: Natural Language and Biological Grounding Guided De Novo Protein Design — a 3.2B protein design model that generates sequences from natural-language function descriptions, optionally conditioned on a ligand or an antigen.
Code: chovak/InstructPro2 · Data: charlesnovak/InstructPro2Bench · Paper: arXiv:2610.19592
Download
export WORK_ROOT=/path/to/workspace # default: ~/instructpro2
huggingface-cli download charlesnovak/InstructPro2 --local-dir $WORK_ROOT/model
Checkpoints
| File / Directory | Parameters | Use |
|---|---|---|
instructpro2_stage1.pt |
2.87B | Pretrained on InstructPro2Bench. Text-conditioned generation, and the starting point for finetuning. |
instructpro2_stage2_ligand.pt |
3.22B | Ligand-binding protein design, conditioned on SMILES. |
instructpro2_stage2_antibody.pt |
3.22B | Antibody design — HCDR1–3 infilling conditioned on an antigen. |
progen2/progen2-large-BFD90/ |
2.7B | Base ProGen2 decoder configuration and weights (Nijkamp et al., 2023; BSD-3-Clause), used for model initialization and Stage 1 pretraining. |
The Stage 2 checkpoints are larger because they carry the gated cross-attention adapters and the frozen ChemBERTa and ESM-2 encoders.
Use
Pass a checkpoint to the scripts in the code repository:
MODEL_CHECKPOINT=$WORK_ROOT/model/instructpro2_stage1.pt bash validate_stage1.sh
MODEL_CHECKPOINT=$WORK_ROOT/model/instructpro2_stage2_ligand.pt bash eval_ligand.sh
MODEL_CHECKPOINT=$WORK_ROOT/model/instructpro2_stage2_antibody.pt bash eval_antibody.sh
The scripts set the architecture mode and the generation settings for each checkpoint; see the code repository's README.
Citation
@article{instructpro2,
title = {InstructPro2: Natural Language and Biological Grounding Guided De Novo Protein Design},
author = {Charles Novak and Zhenqiao Song and Chuan Li and Jianwen Xie and Lei Li},
journal = {arXiv preprint arXiv:2610.19592},
year = {2026}
}
Identity and Version
- Repository
- charlesnovak/InstructPro2
- Publisher
- Charles Novak
- Task
- Not stated by the source
- Modality
- Other
- Library
- fairseq
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- a804b80e49cbe188091145eba26c1bddc563a879
- First published
- 2026-10-13
- Last updated
- 2026-10-16
Files and Weights
7 files, 24.2 GB in total. The weights are 4 files totalling 24.2 GB in bin, pt.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| instructpro2_stage1.pt | Weights | 5.7 GB | 863826e8ea30 |
| instructpro2_stage2_antibody.pt | Weights | 6.4 GB | 869cd0547aa3 |
| instructpro2_stage2_ligand.pt | Weights | 6.4 GB | ce150fbe6d86 |
| progen2/progen2-large-BFD90/pytorch_model.bin | Weights | 5.6 GB | 9c81810054fd |
| progen2/progen2-large-BFD90/config.json | Configuration | 832 B | — |
| README.md | Documentation | 2.5 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 24.2 GB
Released by Charles Novak through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2206.13517
- Described by arXiv:2610.19592
- Trained on (disclosed) charlesnovak/InstructPro2Bench
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 24.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About InstructPro2
Can I use InstructPro2 commercially?
Yes. InstructPro2 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.