Downloads · 30 days
147
84% of all-time downloads
NT-v2-250M-fish20-adapted
bioinfoihb/NT-v2-250M-fish20-adapted
NT-v2-250M-fish20-adapted is a fill-mask model from bioinfoihb. Use it when you need the model to fill a missing word. It is set up for transformers.
This checkpoint is NT-v2-250M adapted to the FishNALM 20-species fish-genome corpus for masked language modeling.
All-time downloads
175
Public
Repo size
941 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin941 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- esm
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- 596a4d74
Try a prompt
Model card
From the Hugging Face model README
NT-v2-250M fish20 adapted
This checkpoint is NT-v2-250M adapted to the FishNALM 20-species fish-genome corpus for masked language modeling.
Domain-adaptive pretraining
| Setting | Value |
|---|---|
| Base model | NT-v2-250M (250M parameters) |
| Tokenization | 6-mer |
| Hardware | 4 × NVIDIA A100 80GB |
| Per-device batch size | 64 |
| Gradient accumulation steps | 1 |
| Effective global batch size | 256 |
| Peak learning rate | 1 × 10⁻⁵ |
| Corpus exposure | 1 epoch |
Usage
This repository contains custom model code. Load it with trust_remote_code=True.
from transformers import AutoModelForMaskedLM, AutoTokenizer
model_id = "<your-namespace>/NT-v2-250M-fish20-adapted"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForMaskedLM.from_pretrained(model_id, trust_remote_code=True)
The checkpoint is intended for DNA-sequence representation and masked-token prediction. Evaluate and adapt it for each downstream task before use.
- Task
- Fill-Mask
- Library
- transformers
- Type
- esm
- Languages
- en
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026