Downloads · 30 days
1.2K
14% of all-time downloads
Metis-4B
IAAR-Shanghai/Metis-4B
Metis-4B is a image-text-to-text model from IAAR-Shanghai. 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 apache-2.0.
Metis-4B is a Metis persistent-memory model built on Qwen/Qwen3.5-4B. The repository contains the complete merged model weights rather than a delta-only checkpoint.
All-time downloads
8.7K
Public
Parameters
5B
10 GB on disk
Likes
6
Public
Repo makeup
Click a slice to open those files.
.safetensors9.9 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- metis
- Access
- Public
- Created
- Jul 16, 2026
- Updated
- Jul 31, 2026
- SHA
- 9242174b
Try a prompt
Base models
Model card
From the Hugging Face model README
Metis-4B
Metis-4B is a Metis persistent-memory model built on Qwen/Qwen3.5-4B.
The repository contains the complete merged model weights rather than a delta-only checkpoint.
Paper
This model is introduced in:
Metis: Memory Foundation Model
Load
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "IAAR-Shanghai/Metis-4B"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_id,
trust_remote_code=True,
dtype=torch.bfloat16,
device_map="auto",
)
Metis uses custom Transformers code included in this repository. Use Transformers 5.4.0 or newer.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- metis
- License
- apache-2.0
- Created
- Jul 16, 2026
- Updated
- Jul 31, 2026