Instructions to use ACIDE/User-VLM-3B-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ACIDE/User-VLM-3B-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="ACIDE/User-VLM-3B-base")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ACIDE/User-VLM-3B-base") model = AutoModelForMultimodalLM.from_pretrained("ACIDE/User-VLM-3B-base") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ACIDE/User-VLM-3B-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ACIDE/User-VLM-3B-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ACIDE/User-VLM-3B-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ACIDE/User-VLM-3B-base
- SGLang
How to use ACIDE/User-VLM-3B-base 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 "ACIDE/User-VLM-3B-base" \ --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": "ACIDE/User-VLM-3B-base", "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 "ACIDE/User-VLM-3B-base" \ --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": "ACIDE/User-VLM-3B-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ACIDE/User-VLM-3B-base with Docker Model Runner:
docker model run hf.co/ACIDE/User-VLM-3B-base
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,7 @@ processor = PaliGemmaProcessor.from_pretrained(model_id)
|
|
| 41 |
model = PaliGemmaForConditionalGeneration.from_pretrained(model_id, torch_dtype=torch.bfloat16).to(device)
|
| 42 |
|
| 43 |
def generate_response(question, image, model, processor):
|
| 44 |
-
prompt = "<image>
|
| 45 |
model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(torch.bfloat16).to(model.device)
|
| 46 |
input_len = model_inputs["input_ids"].shape[-1]
|
| 47 |
|
|
|
|
| 41 |
model = PaliGemmaForConditionalGeneration.from_pretrained(model_id, torch_dtype=torch.bfloat16).to(device)
|
| 42 |
|
| 43 |
def generate_response(question, image, model, processor):
|
| 44 |
+
prompt = f"<image> <|im_start|>USER: {question}<|im_end|> ASSISTANT:"
|
| 45 |
model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(torch.bfloat16).to(model.device)
|
| 46 |
input_len = model_inputs["input_ids"].shape[-1]
|
| 47 |
|