Image-to-Text
Transformers
Safetensors
phi3_v
text-generation
chart-captioning
multimodal
vision-language-model
custom_code
Instructions to use junyoung-00/Phi-3.5-vision-instruct-ChartCap with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use junyoung-00/Phi-3.5-vision-instruct-ChartCap 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="junyoung-00/Phi-3.5-vision-instruct-ChartCap", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("junyoung-00/Phi-3.5-vision-instruct-ChartCap", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from junyoung-00/Phi-3.5-vision-instruct-ChartCap: direct link, hf CLI and curl.
- Browser
- Download file 512 Bytes
-
https://huggingface.co/junyoung-00/Phi-3.5-vision-instruct-ChartCap/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://junyoung-00/Phi-3.5-vision-instruct-ChartCap/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/junyoung-00/Phi-3.5-vision-instruct-ChartCap/resolve/main/preprocessor_config.json
512 Bytes
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "microsoft/Phi-3.5-vision-instruct--processing_phi3_v.Phi3VImageProcessor", | |
| "AutoProcessor": "microsoft/Phi-3.5-vision-instruct--processing_phi3_v.Phi3VProcessor" | |
| }, | |
| "do_convert_rgb": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "Phi3VImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "num_crops": 4, | |
| "num_img_tokens": 144, | |
| "processor_class": "Phi3VProcessor" | |
| } | |