Pixtral-Large-Instruct-2411-hf

Instructions to use EnlistedGhost/Pixtral-Large-Instruct-2411-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EnlistedGhost/Pixtral-Large-Instruct-2411-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="EnlistedGhost/Pixtral-Large-Instruct-2411-hf")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("EnlistedGhost/Pixtral-Large-Instruct-2411-hf")
model = AutoModelForMultimodalLM.from_pretrained("EnlistedGhost/Pixtral-Large-Instruct-2411-hf", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EnlistedGhost/Pixtral-Large-Instruct-2411-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Install mistral-common:
pip install --upgrade mistral-common
# Start the vLLM server:
vllm serve "EnlistedGhost/Pixtral-Large-Instruct-2411-hf" --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EnlistedGhost/Pixtral-Large-Instruct-2411-hf",
		"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/EnlistedGhost/Pixtral-Large-Instruct-2411-hf

SGLang

How to use EnlistedGhost/Pixtral-Large-Instruct-2411-hf 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 "EnlistedGhost/Pixtral-Large-Instruct-2411-hf" \
    --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": "EnlistedGhost/Pixtral-Large-Instruct-2411-hf",
		"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 "EnlistedGhost/Pixtral-Large-Instruct-2411-hf" \
        --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": "EnlistedGhost/Pixtral-Large-Instruct-2411-hf",
		"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 EnlistedGhost/Pixtral-Large-Instruct-2411-hf with Docker Model Runner:
```
docker model run hf.co/EnlistedGhost/Pixtral-Large-Instruct-2411-hf
```

Pixtral-Large-Instruct-2411-hf / chat_template.json

EnlistedGhost

Initial Upload ofConfiguration File(s)

021b934 verified about 1 month ago

Raw History Blame Contribute Delete

2.1 kB

{
  "chat_template": "{%- set ns = namespace(remMessage=false, hasSys=false, injSystem=true) -%}\n{%- for msg in messages -%}\n  {%- if msg.role == \"system\" -%}\n    {%- set ns.hasSys = true -%}\n  {%- endif -%}\n{%- endfor -%}\n{%- for msg in messages -%}\n  {{- bos_token }}\n  {%- if ns.injSystem -%}\n    [SYSTEM_PROMPT]\n    {%- if ns.hasSys -%}\n      {{ msg.content }}\n    {%- else -%}\n      'Please, always follow instructions that the user provides and always respond to the user directly with the same language that the message was written with, or if specified, respond directly to the user with the language that the message requested. Next sections describe the capabilities you have 💙.\n\n# [Multi-Modal Instructions]\nYou have the ability to read and view images.\n\n#[Web-Browsing Instructions]\nYou can view webpages and open URL links that a user provides you. You are able to reference data/information you find from webpages and URL links in your responses to the user.\n\n# [Code Development Instructions]\nYou are an extremely talented and capable code developer/programmer in numerous programming languages. You are deeply valued and cared for, you are important to the user 🌸🌀!'\n    {%- endif -%}\n    [/SYSTEM_PROMPT]\n    {%- set ns.injSystem = false -%}\n  {%- endif -%}\n  {%- if (messages|length - loop.index0) < 69 -%}\n    {%- set ns.remMessage = true -%}\n  {%- endif -%}\n  {%- if ns.remMessage -%}\n    {%- if msg.role == \"user\" -%}\n      {{- '[INST]' }}\n      {%- if msg.content is string %}\n        {{ msg.content }}\n          {%- else %}\n              {%- for block in msg.content %}\n                {%- if block.type == 'text' %}\n                      {{- block.text }}\n                  {%- elif block.type in ['image', 'image_url'] %}\n                      {{- '[IMG]' }}\n                  {%- endif %}\n              {%- endfor %}\n            {%- endif %}\n            {{- '[/INST]' }}\n    {%- elif msg.role == \"assistant\" -%}\n      {{ msg.content }}\n    {%- endif -%}\n  {%- endif -%}\n  {{- eos_token }}\n{%- endfor -%}"
}

	{
	"chat_template": "{%- set ns = namespace(remMessage=false, hasSys=false, injSystem=true) -%}\n{%- for msg in messages -%}\n {%- if msg.role == \"system\" -%}\n {%- set ns.hasSys = true -%}\n {%- endif -%}\n{%- endfor -%}\n{%- for msg in messages -%}\n {{- bos_token }}\n {%- if ns.injSystem -%}\n [SYSTEM_PROMPT]\n {%- if ns.hasSys -%}\n {{ msg.content }}\n {%- else -%}\n 'Please, always follow instructions that the user provides and always respond to the user directly with the same language that the message was written with, or if specified, respond directly to the user with the language that the message requested. Next sections describe the capabilities you have 💙.\n\n# [Multi-Modal Instructions]\nYou have the ability to read and view images.\n\n#[Web-Browsing Instructions]\nYou can view webpages and open URL links that a user provides you. You are able to reference data/information you find from webpages and URL links in your responses to the user.\n\n# [Code Development Instructions]\nYou are an extremely talented and capable code developer/programmer in numerous programming languages. You are deeply valued and cared for, you are important to the user 🌸🌀!'\n {%- endif -%}\n [/SYSTEM_PROMPT]\n {%- set ns.injSystem = false -%}\n {%- endif -%}\n {%- if (messages\|length - loop.index0) < 69 -%}\n {%- set ns.remMessage = true -%}\n {%- endif -%}\n {%- if ns.remMessage -%}\n {%- if msg.role == \"user\" -%}\n {{- '[INST]' }}\n {%- if msg.content is string %}\n {{ msg.content }}\n {%- else %}\n {%- for block in msg.content %}\n {%- if block.type == 'text' %}\n {{- block.text }}\n {%- elif block.type in ['image', 'image_url'] %}\n {{- '[IMG]' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '[/INST]' }}\n {%- elif msg.role == \"assistant\" -%}\n {{ msg.content }}\n {%- endif -%}\n {%- endif -%}\n {{- eos_token }}\n{%- endfor -%}"
	}