Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

TheFinAI
/
FinLLaVA

Image-Text-to-Text
Transformers
Safetensors
English
llava_llama
text-generation
Model card Files Files and versions
xet
Community
6

Instructions to use TheFinAI/FinLLaVA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use TheFinAI/FinLLaVA with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("image-text-to-text", model="TheFinAI/FinLLaVA")
    # Load model directly
    from transformers import AutoModelForCausalLM
    model = AutoModelForCausalLM.from_pretrained("TheFinAI/FinLLaVA", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • vLLM

    How to use TheFinAI/FinLLaVA with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "TheFinAI/FinLLaVA"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "TheFinAI/FinLLaVA",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
    Use Docker
    docker model run hf.co/TheFinAI/FinLLaVA
  • SGLang

    How to use TheFinAI/FinLLaVA 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 "TheFinAI/FinLLaVA" \
        --host 0.0.0.0 \
        --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "TheFinAI/FinLLaVA",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
    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 "TheFinAI/FinLLaVA" \
            --host 0.0.0.0 \
            --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "TheFinAI/FinLLaVA",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
  • Docker Model Runner

    How to use TheFinAI/FinLLaVA with Docker Model Runner:

    docker model run hf.co/TheFinAI/FinLLaVA

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Gated model
You can list files but not access them

Preview of files found in this repository
  • __pycache__
    Upload 95 files (#2) over 1 year ago
  • language_model
    Upload 95 files (#2) over 1 year ago
  • multimodal_encoder
    Upload 95 files (#2) over 1 year ago
  • multimodal_projector
    Upload 95 files (#2) over 1 year ago
  • __init__.py
    350 Bytes
    Upload 95 files (#2) over 1 year ago
  • apply_delta.py
    1.96 kB
    Upload 95 files (#2) over 1 year ago
  • builder.py
    9.34 kB
    Upload 95 files (#2) over 1 year ago
  • consolidate.py
    928 Bytes
    Upload 95 files (#2) over 1 year ago
  • llava_arch.py
    18.1 kB
    Upload 95 files (#2) over 1 year ago
  • make_delta.py
    2.26 kB
    Upload 95 files (#2) over 1 year ago
  • utils.py
    927 Bytes
    Upload 95 files (#2) over 1 year ago