Instructions to use dxkrnn/blip-ds-handdrawn-phase-one with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dxkrnn/blip-ds-handdrawn-phase-one with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="dxkrnn/blip-ds-handdrawn-phase-one")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("dxkrnn/blip-ds-handdrawn-phase-one") model = AutoModelForMultimodalLM.from_pretrained("dxkrnn/blip-ds-handdrawn-phase-one", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dxkrnn/blip-ds-handdrawn-phase-one with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dxkrnn/blip-ds-handdrawn-phase-one" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dxkrnn/blip-ds-handdrawn-phase-one", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dxkrnn/blip-ds-handdrawn-phase-one
- SGLang
How to use dxkrnn/blip-ds-handdrawn-phase-one 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 "dxkrnn/blip-ds-handdrawn-phase-one" \ --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": "dxkrnn/blip-ds-handdrawn-phase-one", "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 "dxkrnn/blip-ds-handdrawn-phase-one" \ --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": "dxkrnn/blip-ds-handdrawn-phase-one", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dxkrnn/blip-ds-handdrawn-phase-one with Docker Model Runner:
docker model run hf.co/dxkrnn/blip-ds-handdrawn-phase-one
Download tokenizer_config.json from dxkrnn/blip-ds-handdrawn-phase-one: direct link, hf CLI and curl.
- Browser
- Download file 527 Bytes
-
https://huggingface.co/dxkrnn/blip-ds-handdrawn-phase-one/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://dxkrnn/blip-ds-handdrawn-phase-one/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/dxkrnn/blip-ds-handdrawn-phase-one/resolve/main/tokenizer_config.json
527 Bytes
| { | |
| "cls_token": "[CLS]", | |
| "do_basic_tokenize": true, | |
| "do_lower_case": true, | |
| "mask_token": "[MASK]", | |
| "model_max_length": 512, | |
| "name_or_path": "Salesforce/blip-image-captioning-large", | |
| "never_split": null, | |
| "pad_token": "[PAD]", | |
| "processor_class": "BlipProcessor", | |
| "sep_token": "[SEP]", | |
| "special_tokens_map_file": null, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "unk_token": "[UNK]", | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ] | |
| } | |