Image-to-Text
Transformers
Safetensors
molparser_vision_encoder_decoder
image-text-to-text
chemistry
custom_code
Instructions to use UniParser/MolParser-Mobile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UniParser/MolParser-Mobile with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="UniParser/MolParser-Mobile", trust_remote_code=True)# Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("UniParser/MolParser-Mobile", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update modeling_molparser_mobile.py
Browse files
modeling_molparser_mobile.py
CHANGED
|
@@ -1,8 +1,5 @@
|
|
| 1 |
"""MolParser Mobile model code for Hugging Face Hub remote loading.
|
| 2 |
|
| 3 |
-
This file intentionally contains only the architecture needed by the released
|
| 4 |
-
MolParser Mobile checkpoint. It omits the training-time model registry for nano,
|
| 5 |
-
small, base, large, and SigLIP variants.
|
| 6 |
"""
|
| 7 |
|
| 8 |
from __future__ import annotations
|
|
|
|
| 1 |
"""MolParser Mobile model code for Hugging Face Hub remote loading.
|
| 2 |
|
|
|
|
|
|
|
|
|
|
| 3 |
"""
|
| 4 |
|
| 5 |
from __future__ import annotations
|