Instructions to use Zero-Vision/Llama-3-MixSenseV1_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zero-Vision/Llama-3-MixSenseV1_1 with Transformers:

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

pipe = pipeline("text-generation", model="Zero-Vision/Llama-3-MixSenseV1_1", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Zero-Vision/Llama-3-MixSenseV1_1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Zero-Vision/Llama-3-MixSenseV1_1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zero-Vision/Llama-3-MixSenseV1_1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zero-Vision/Llama-3-MixSenseV1_1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Zero-Vision/Llama-3-MixSenseV1_1

SGLang

How to use Zero-Vision/Llama-3-MixSenseV1_1 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 "Zero-Vision/Llama-3-MixSenseV1_1" \
    --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": "Zero-Vision/Llama-3-MixSenseV1_1",
		"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 "Zero-Vision/Llama-3-MixSenseV1_1" \
        --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": "Zero-Vision/Llama-3-MixSenseV1_1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Zero-Vision/Llama-3-MixSenseV1_1 with Docker Model Runner:
```
docker model run hf.co/Zero-Vision/Llama-3-MixSenseV1_1
```

Llama-3-MixSenseV1_1 / llama3mixsense.py

xrx

Initial commit

c3314a5 about 2 years ago

Raw History Blame Contribute Delete

1.73 kB

	'''
	This file if for VLMEvalKit.
	'''
	import torch
	import transformers
	from transformers import AutoModelForCausalLM, AutoTokenizer
	from PIL import Image
	import warnings

	from .base import BaseModel
	from ..smp import *
	from ..utils import DATASET_TYPE


	class LLama3Mixsense(BaseModel):

	INSTALL_REQ = False
	INTERLEAVE = False

	def __init__(self, model_path="Zero-Vision/Llama-3-MixSenseV1_1", **kwargs):
	assert model_path is not None
	transformers.logging.set_verbosity_error()
	transformers.logging.disable_progress_bar()
	warnings.filterwarnings("ignore")
	self.tokenizer = AutoTokenizer.from_pretrained(
	model_path, trust_remote_code=True
	)
	self.model = AutoModelForCausalLM.from_pretrained(
	model_path, device_map="auto", trust_remote_code=True
	)
	self.kwargs = kwargs

	def generate_inner(self, message, dataset=None):
	prompt, image_path = self.message_to_promptimg(message)
	input_ids=self.model.text_process(prompt, self.tokenizer)
	image = Image.open(image_path).convert("RGB")
	image_tensor = self.model.image_process([image]).to(dtype=self.model.dtype, device=device)
	# generate
	with torch.inference_mode():
	output_ids = self.model.generate(
	input_ids,
	images=image_tensor,
	max_new_tokens=2048,
	use_cache=True,
	eos_token_id=[
	self.tokenizer.eos_token_id,
	self.tokenizer.convert_tokens_to_ids(["<\|eot_id\|>"])[0],
	],
	)
	return self.tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()