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

Libraries

How to use codeShare/joycaption_beta_one_SDNQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="codeShare/joycaption_beta_one_SDNQ")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("codeShare/joycaption_beta_one_SDNQ")
model = AutoModelForImageTextToText.from_pretrained("codeShare/joycaption_beta_one_SDNQ")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codeShare/joycaption_beta_one_SDNQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codeShare/joycaption_beta_one_SDNQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codeShare/joycaption_beta_one_SDNQ",
		"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/codeShare/joycaption_beta_one_SDNQ

SGLang

How to use codeShare/joycaption_beta_one_SDNQ 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 "codeShare/joycaption_beta_one_SDNQ" \
    --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": "codeShare/joycaption_beta_one_SDNQ",
		"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 "codeShare/joycaption_beta_one_SDNQ" \
        --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": "codeShare/joycaption_beta_one_SDNQ",
		"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 codeShare/joycaption_beta_one_SDNQ with Docker Model Runner:
```
docker model run hf.co/codeShare/joycaption_beta_one_SDNQ
```

codeShare commited on 19 days ago

Commit

aeb9967

verified ·

1 Parent(s): 663cd4d

Delete chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +0 -43

chat_template.jinja DELETED Viewed

@@ -1,43 +0,0 @@
-{%- if not date_string is defined %}
-    {%- set date_string = "26 July 2024" %}
-{%- endif %}
-{#- This block extracts the system message, so we can slot it into the right place. #}
-{%- if messages[0]['role'] == 'system' %}
-    {%- set system_message = messages[0]['content'] %}
-    {%- set messages = messages[1:] %}
-{%- else %}
-    {%- set system_message = "" %}
-{%- endif %}
-{#- System message + builtin tools #}
-{{- "<|start_header_id|>system<|end_header_id|>
-" }}
-{{- "Cutting Knowledge Date: December 2023
-" }}
-{{- "Today Date: " + date_string + "
-" }}
-{{- system_message }}
-{{- "<|eot_id|>" }}
-{%- set first_user_message = True %}
-{%- for message in messages %}
-    {%- if first_user_message and message['role'] == 'user' %}
-		{%- set first_user_message = False %}
-	    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>
-<|reserved_special_token_70|><|reserved_special_token_69|><|reserved_special_token_71|>'+ message['content'].replace('<|reserved_special_token_69|>', '').lstrip() + '<|eot_id|>' }}
-	{%- else %}
-        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>
-'+ message['content'] + '<|eot_id|>' }}
-	{%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|start_header_id|>assistant<|end_header_id|>
-' }}
-{%- endif %}