Instructions to use Efficient-Large-Model/VILA1.5-40b-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Efficient-Large-Model/VILA1.5-40b-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="Efficient-Large-Model/VILA1.5-40b-AWQ")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Efficient-Large-Model/VILA1.5-40b-AWQ", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Efficient-Large-Model/VILA1.5-40b-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Efficient-Large-Model/VILA1.5-40b-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Efficient-Large-Model/VILA1.5-40b-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Efficient-Large-Model/VILA1.5-40b-AWQ

SGLang

How to use Efficient-Large-Model/VILA1.5-40b-AWQ 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 "Efficient-Large-Model/VILA1.5-40b-AWQ" \
    --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": "Efficient-Large-Model/VILA1.5-40b-AWQ",
		"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 "Efficient-Large-Model/VILA1.5-40b-AWQ" \
        --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": "Efficient-Large-Model/VILA1.5-40b-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Efficient-Large-Model/VILA1.5-40b-AWQ with Docker Model Runner:
```
docker model run hf.co/Efficient-Large-Model/VILA1.5-40b-AWQ
```

Update config.json

by waitingkuo - opened Sep 24, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -163,7 +163,7 @@
   "mm_vision_select_feature": "patch",
   "mm_vision_select_layer": -1,
   "model_dtype": "torch.bfloat16",
-  "model_type": "llava_llama",
   "num_video_frames": 8,
   "resume_path": "vila1.5-34b",
   "s2": false,

   "mm_vision_select_feature": "patch",
   "mm_vision_select_layer": -1,
   "model_dtype": "torch.bfloat16",
+  "model_type": "llava",
   "num_video_frames": 8,
   "resume_path": "vila1.5-34b",
   "s2": false,