Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

laicsiifes
/
phi3-vision-flickr30k_pt_human_generated

Image-Text-to-Text
Transformers
Safetensors
Portuguese
conversational
Eval Results (legacy)
Model card Files Files and versions
xet
Community
1

Instructions to use laicsiifes/phi3-vision-flickr30k_pt_human_generated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use laicsiifes/phi3-vision-flickr30k_pt_human_generated with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("image-text-to-text", model="laicsiifes/phi3-vision-flickr30k_pt_human_generated")
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
                {"type": "text", "text": "What animal is on the candy?"}
            ]
        },
    ]
    pipe(text=messages)
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("laicsiifes/phi3-vision-flickr30k_pt_human_generated", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • vLLM

    How to use laicsiifes/phi3-vision-flickr30k_pt_human_generated with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "laicsiifes/phi3-vision-flickr30k_pt_human_generated"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "laicsiifes/phi3-vision-flickr30k_pt_human_generated",
    		"messages": [
    			{
    				"role": "user",
    				"content": [
    					{
    						"type": "text",
    						"text": "Describe this image in one sentence."
    					},
    					{
    						"type": "image_url",
    						"image_url": {
    							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
    						}
    					}
    				]
    			}
    		]
    	}'
    Use Docker
    docker model run hf.co/laicsiifes/phi3-vision-flickr30k_pt_human_generated
  • SGLang

    How to use laicsiifes/phi3-vision-flickr30k_pt_human_generated with SGLang:

    Install from pip and serve model
    # Install SGLang from pip:
    pip install sglang
    # Start the SGLang server:
    python3 -m sglang.launch_server \
        --model-path "laicsiifes/phi3-vision-flickr30k_pt_human_generated" \
        --host 0.0.0.0 \
        --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "laicsiifes/phi3-vision-flickr30k_pt_human_generated",
    		"messages": [
    			{
    				"role": "user",
    				"content": [
    					{
    						"type": "text",
    						"text": "Describe this image in one sentence."
    					},
    					{
    						"type": "image_url",
    						"image_url": {
    							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
    						}
    					}
    				]
    			}
    		]
    	}'
    Use Docker images
    docker run --gpus all \
        --shm-size 32g \
        -p 30000:30000 \
        -v ~/.cache/huggingface:/root/.cache/huggingface \
        --env "HF_TOKEN=<secret>" \
        --ipc=host \
        lmsysorg/sglang:latest \
        python3 -m sglang.launch_server \
            --model-path "laicsiifes/phi3-vision-flickr30k_pt_human_generated" \
            --host 0.0.0.0 \
            --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "laicsiifes/phi3-vision-flickr30k_pt_human_generated",
    		"messages": [
    			{
    				"role": "user",
    				"content": [
    					{
    						"type": "text",
    						"text": "Describe this image in one sentence."
    					},
    					{
    						"type": "image_url",
    						"image_url": {
    							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
    						}
    					}
    				]
    			}
    		]
    	}'
  • Docker Model Runner

    How to use laicsiifes/phi3-vision-flickr30k_pt_human_generated with Docker Model Runner:

    docker model run hf.co/laicsiifes/phi3-vision-flickr30k_pt_human_generated
phi3-vision-flickr30k_pt_human_generated
729 MB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 10 commits
hilariooliveira's picture
hilariooliveira
gabrielmotablima's picture
gabrielmotablima
Update README.md (#1)
3b000e9 verified 4 months ago
  • .gitattributes
    1.57 kB
    Update README.md (#1) 4 months ago
  • README.md
    4.29 kB
    Update README.md (#1) 4 months ago
  • adapter_config.json
    850 Bytes
    Upload model 6 months ago
  • adapter_model.safetensors
    725 MB
    xet
    Upload model 6 months ago
  • chat_template.json
    249 Bytes
    Upload processor 7 months ago
  • example.png
    435 kB
    xet
    Update README.md (#1) 4 months ago
  • preprocessor_config.json
    525 Bytes
    Upload processor 7 months ago
  • special_tokens_map.json
    670 Bytes
    Upload processor 7 months ago
  • tokenizer.json
    3.63 MB
    Upload processor 7 months ago
  • tokenizer_config.json
    9.47 kB
    Upload processor 7 months ago