Instructions to use wdfshit/Phi-3.5-vision-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wdfshit/Phi-3.5-vision-instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="wdfshit/Phi-3.5-vision-instruct", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("wdfshit/Phi-3.5-vision-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use wdfshit/Phi-3.5-vision-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wdfshit/Phi-3.5-vision-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wdfshit/Phi-3.5-vision-instruct",
		"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/wdfshit/Phi-3.5-vision-instruct

SGLang

How to use wdfshit/Phi-3.5-vision-instruct 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 "wdfshit/Phi-3.5-vision-instruct" \
    --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": "wdfshit/Phi-3.5-vision-instruct",
		"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 "wdfshit/Phi-3.5-vision-instruct" \
        --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": "wdfshit/Phi-3.5-vision-instruct",
		"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 wdfshit/Phi-3.5-vision-instruct with Docker Model Runner:
```
docker model run hf.co/wdfshit/Phi-3.5-vision-instruct
```

Phi-3.5-vision-instruct / tokenizer_config.json

wdfshit

Duplicate from microsoft/Phi-3.5-vision-instruct

0a44ed2 3 months ago

raw

history blame contribute delete

9.52 kB

	{
	"add_bos_token": true,
	"add_eos_token": false,
	"added_tokens_decoder": {
	"0": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": false
	},
	"32000": {
	"content": "<\|endoftext\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32001": {
	"content": "<\|assistant\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32002": {
	"content": "<\|placeholder1\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32003": {
	"content": "<\|placeholder2\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32004": {
	"content": "<\|placeholder3\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32005": {
	"content": "<\|placeholder4\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32006": {
	"content": "<\|system\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32007": {
	"content": "<\|end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32008": {
	"content": "<\|placeholder5\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32009": {
	"content": "<\|placeholder6\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32010": {
	"content": "<\|user\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32011": {
	"content": "<\|placeholder7\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32012": {
	"content": "<\|placeholder8\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32013": {
	"content": "<\|placeholder9\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32014": {
	"content": "<\|placeholder10\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32015": {
	"content": "<\|placeholder11\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32016": {
	"content": "<\|placeholder12\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32017": {
	"content": "<\|placeholder13\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32018": {
	"content": "<\|placeholder14\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32019": {
	"content": "<\|placeholder15\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32020": {
	"content": "<\|placeholder16\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32021": {
	"content": "<\|placeholder17\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32022": {
	"content": "<\|placeholder18\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32023": {
	"content": "<\|placeholder19\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32024": {
	"content": "<\|placeholder20\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32025": {
	"content": "<\|placeholder21\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32026": {
	"content": "<\|placeholder22\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32027": {
	"content": "<\|placeholder23\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32028": {
	"content": "<\|placeholder24\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32029": {
	"content": "<\|placeholder25\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32030": {
	"content": "<\|placeholder26\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32031": {
	"content": "<\|placeholder27\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32032": {
	"content": "<\|placeholder28\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32033": {
	"content": "<\|placeholder29\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32034": {
	"content": "<\|placeholder30\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32035": {
	"content": "<\|placeholder31\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32036": {
	"content": "<\|placeholder32\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32037": {
	"content": "<\|placeholder33\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32038": {
	"content": "<\|placeholder34\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32039": {
	"content": "<\|placeholder35\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32040": {
	"content": "<\|placeholder36\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32041": {
	"content": "<\|placeholder37\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32042": {
	"content": "<\|placeholder38\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32043": {
	"content": "<\|placeholder39\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	},
	"32044": {
	"content": "<\|image\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": true
	}
	},
	"additional_special_tokens": [
	"<\|system\|>",
	"<\|end\|>",
	"<\|user\|>",
	"<\|end\|>"
	],
	"auto_map": {
	"AutoProcessor": "processing_phi3_v.Phi3VProcessor"
	},
	"bos_token": "<s>",
	"chat_template": "{% for message in messages %}{{'<\|' + message['role'] + '\|>' + '\n' + message['content'] + '<\|end\|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<\|assistant\|>\n' -}}{% endif %}",
	"clean_up_tokenization_spaces": false,
	"eos_token": "<\|endoftext\|>",
	"legacy": false,
	"model_max_length": 131072,
	"pad_token": "<\|endoftext\|>",
	"padding_side": "right",
	"processor_class": "Phi3VProcessor",
	"sp_model_kwargs": {},
	"tokenizer_class": "LlamaTokenizer",
	"unk_token": "<unk>",
	"use_default_system_prompt": false
	}