Instructions to use MYTH-Lab/VW-LMM-Vicuna-pif-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MYTH-Lab/VW-LMM-Vicuna-pif-7b with Transformers:

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

pipe = pipeline("text-generation", model="MYTH-Lab/VW-LMM-Vicuna-pif-7b")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("MYTH-Lab/VW-LMM-Vicuna-pif-7b")
model = AutoModelForCausalLM.from_pretrained("MYTH-Lab/VW-LMM-Vicuna-pif-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MYTH-Lab/VW-LMM-Vicuna-pif-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MYTH-Lab/VW-LMM-Vicuna-pif-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MYTH-Lab/VW-LMM-Vicuna-pif-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MYTH-Lab/VW-LMM-Vicuna-pif-7b

SGLang

How to use MYTH-Lab/VW-LMM-Vicuna-pif-7b 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 "MYTH-Lab/VW-LMM-Vicuna-pif-7b" \
    --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": "MYTH-Lab/VW-LMM-Vicuna-pif-7b",
		"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 "MYTH-Lab/VW-LMM-Vicuna-pif-7b" \
        --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": "MYTH-Lab/VW-LMM-Vicuna-pif-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MYTH-Lab/VW-LMM-Vicuna-pif-7b with Docker Model Runner:
```
docker model run hf.co/MYTH-Lab/VW-LMM-Vicuna-pif-7b
```

Potentialts commited on Mar 14, 2024

Commit

722c750

verified ·

1 Parent(s): c26b9c4

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ inference: false
 This repo contains the weights of VW-LMM-Vicuna-pif-7b proposed in paper "Multi-modal Auto-regressive Modeling via Visual Words"
-The term "pif" in the model name stands for "<strong>p</strong>seudo <strong>i</strong>mage <strong>f</strong>eatures". This model is capable of accepting pseudo-image features constructed using the VW_head and word embeddings of the model as a substitute for real image inputs.
 For specific usage and chat templates, please refer to our project repo https://github.com/pengts/VW-LMM

 This repo contains the weights of VW-LMM-Vicuna-pif-7b proposed in paper "Multi-modal Auto-regressive Modeling via Visual Words"
+The term "pif" in the model name stands for "<strong>p</strong>seudo <strong>i</strong>mage <strong>f</strong>eatures". This model is capable of accepting pseudo-image features constructed using the VM_head and word embeddings of the model as a substitute for real image inputs.
 For specific usage and chat templates, please refer to our project repo https://github.com/pengts/VW-LMM