Image-to-Text
Transformers
Safetensors
Japanese
llava-jp
text-generation
vision
image-captioning
VQA
Instructions to use toshi456/llava-jp-1.3b-v1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use toshi456/llava-jp-1.3b-v1.1 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="toshi456/llava-jp-1.3b-v1.1")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("toshi456/llava-jp-1.3b-v1.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -62,9 +62,6 @@ from llava.train.dataset import tokenizer_image_token
|
|
| 62 |
|
| 63 |
|
| 64 |
if __name__ == "__main__":
|
| 65 |
-
parser = transformers.HfArgumentParser(
|
| 66 |
-
(ModelArguments, DataArguments, TrainingArguments))
|
| 67 |
-
model_args, data_args, training_args = parser.parse_args_into_dataclasses()
|
| 68 |
model_path = 'toshi456/llava-jp-1.3b-v1.1'
|
| 69 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 70 |
torch_dtype = torch.bfloat16 if device=="cuda" else torch.float32
|
|
|
|
| 62 |
|
| 63 |
|
| 64 |
if __name__ == "__main__":
|
|
|
|
|
|
|
|
|
|
| 65 |
model_path = 'toshi456/llava-jp-1.3b-v1.1'
|
| 66 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 67 |
torch_dtype = torch.bfloat16 if device=="cuda" else torch.float32
|