Downloads · 30 days
36
52% of all-time downloads
bio-posttrain-gemma4-e2b-rna-sft
mims-harvard/bio-posttrain-gemma4-e2b-rna-sft
bio-posttrain-gemma4-e2b-rna-sft is a image-text-to-text model from mims-harvard. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gemma.
RNA supervised fine-tuning (SFT) checkpoint from How Post-Training Shapes Biological Reasoning Models.
All-time downloads
69
Public
Parameters
5.5B
22.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors22 GB · 100%
Parameter types
How the weights are stored.
F325.5B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Bio-posttrain Gemma-4-E2B RNA SFT
RNA supervised fine-tuning (SFT) checkpoint from How Post-Training Shapes Biological Reasoning Models.
Model details
- Base model:
google/gemma-4-E2B-it - RNA embeddings: Precomputed TranscriptFormer (2048-d), projected via
rna_projection.pt - LoRA: rank 32, alpha 64
- Validation loss: 0.9227
Files
| File | Description |
|---|---|
model.safetensors | Merged LLM weights |
rna_projection.pt | Linear map RNA embed (2048) → text hidden |
rna_model_config.json | Architecture metadata |
Loading
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained("mims-harvard/bio-posttrain-gemma4-e2b-rna-sft", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("mims-harvard/bio-posttrain-gemma4-e2b-rna-sft")
proj = torch.load("rna_projection.pt", map_location="cpu")
RNA sequence embeddings are supplied offline at inference time. See the rna_models code in the BioReason repository.
Collection
Part of the Bio-posttrain collection.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma4
- License
- gemma
- Created
- Jun 22, 2026
- Updated
- Jun 22, 2026