Instructions to use besiktas/clippy-pali with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use besiktas/clippy-pali with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="besiktas/clippy-pali")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("besiktas/clippy-pali") model = AutoModelForImageTextToText.from_pretrained("besiktas/clippy-pali") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use besiktas/clippy-pali with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "besiktas/clippy-pali" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "besiktas/clippy-pali", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/besiktas/clippy-pali
- SGLang
How to use besiktas/clippy-pali 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 "besiktas/clippy-pali" \ --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": "besiktas/clippy-pali", "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 "besiktas/clippy-pali" \ --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": "besiktas/clippy-pali", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use besiktas/clippy-pali with Docker Model Runner:
docker model run hf.co/besiktas/clippy-pali
Upload processor
Browse files- preprocessor_config.json +0 -3
- tokenizer_config.json +0 -3
preprocessor_config.json
CHANGED
|
@@ -14,9 +14,6 @@
|
|
| 14 |
"input_data_format",
|
| 15 |
"do_convert_rgb"
|
| 16 |
],
|
| 17 |
-
"auto_map": {
|
| 18 |
-
"AutoProcessor": "paligemma_model.PaliGemmaProcessor"
|
| 19 |
-
},
|
| 20 |
"do_convert_rgb": null,
|
| 21 |
"do_normalize": true,
|
| 22 |
"do_rescale": true,
|
|
|
|
| 14 |
"input_data_format",
|
| 15 |
"do_convert_rgb"
|
| 16 |
],
|
|
|
|
|
|
|
|
|
|
| 17 |
"do_convert_rgb": null,
|
| 18 |
"do_normalize": true,
|
| 19 |
"do_rescale": true,
|
tokenizer_config.json
CHANGED
|
@@ -10966,9 +10966,6 @@
|
|
| 10966 |
"additional_special_tokens": [
|
| 10967 |
"<image>"
|
| 10968 |
],
|
| 10969 |
-
"auto_map": {
|
| 10970 |
-
"AutoProcessor": "paligemma_model.PaliGemmaProcessor"
|
| 10971 |
-
},
|
| 10972 |
"bos_token": "<bos>",
|
| 10973 |
"clean_up_tokenization_spaces": false,
|
| 10974 |
"eos_token": "<eos>",
|
|
|
|
| 10966 |
"additional_special_tokens": [
|
| 10967 |
"<image>"
|
| 10968 |
],
|
|
|
|
|
|
|
|
|
|
| 10969 |
"bos_token": "<bos>",
|
| 10970 |
"clean_up_tokenization_spaces": false,
|
| 10971 |
"eos_token": "<eos>",
|