Any-to-Any
Transformers
Safetensors
English
ovis_u1
text-generation
image-text-to-text
image-to-text
text-to-image
image-to-image
custom_code
Instructions to use monurcan/Ovis-U1-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use monurcan/Ovis-U1-3B with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("monurcan/Ovis-U1-3B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update modeling_aimv2.py
Browse files- modeling_aimv2.py +1 -1
modeling_aimv2.py
CHANGED
|
@@ -339,7 +339,7 @@ class AIMv2Transformer(nn.Module):
|
|
| 339 |
|
| 340 |
class AIMv2PretrainedModel(PreTrainedModel):
|
| 341 |
config_class = AIMv2Config
|
| 342 |
-
base_model_prefix = "
|
| 343 |
supports_gradient_checkpointing = True
|
| 344 |
main_input_name = "pixel_values"
|
| 345 |
_no_split_modules = ["AIMv2ViTPreprocessor", "AIMv2Block"]
|
|
|
|
| 339 |
|
| 340 |
class AIMv2PretrainedModel(PreTrainedModel):
|
| 341 |
config_class = AIMv2Config
|
| 342 |
+
base_model_prefix = "aimv2onur"
|
| 343 |
supports_gradient_checkpointing = True
|
| 344 |
main_input_name = "pixel_values"
|
| 345 |
_no_split_modules = ["AIMv2ViTPreprocessor", "AIMv2Block"]
|