Instructions to use Efficient-Large-Model/VILA15-40b-hf-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Efficient-Large-Model/VILA15-40b-hf-preview with Transformers:

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

pipe = pipeline("text-generation", model="Efficient-Large-Model/VILA15-40b-hf-preview", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Efficient-Large-Model/VILA15-40b-hf-preview", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Efficient-Large-Model/VILA15-40b-hf-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Efficient-Large-Model/VILA15-40b-hf-preview"
# 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/VILA15-40b-hf-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Efficient-Large-Model/VILA15-40b-hf-preview

SGLang

How to use Efficient-Large-Model/VILA15-40b-hf-preview 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/VILA15-40b-hf-preview" \
    --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/VILA15-40b-hf-preview",
		"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/VILA15-40b-hf-preview" \
        --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/VILA15-40b-hf-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Efficient-Large-Model/VILA15-40b-hf-preview with Docker Model Runner:
```
docker model run hf.co/Efficient-Large-Model/VILA15-40b-hf-preview
```

VILA15-40b-hf-preview / constants.py

Ligeng-Zhu

Upload files with vila-upload.

48c35d1 verified over 1 year ago

raw

history blame contribute delete

1.96 kB

	# Copyright 2024 NVIDIA CORPORATION & AFFILIATES
	#
	# Licensed under the Apache License, Version 2.0 (the "License");
	# you may not use this file except in compliance with the License.
	# You may obtain a copy of the License at
	#
	# http://www.apache.org/licenses/LICENSE-2.0
	#
	# Unless required by applicable law or agreed to in writing, software
	# distributed under the License is distributed on an "AS IS" BASIS,
	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
	# See the License for the specific language governing permissions and
	# limitations under the License.
	#
	# SPDX-License-Identifier: Apache-2.0

	CONTROLLER_HEART_BEAT_EXPIRATION = 30
	WORKER_HEART_BEAT_INTERVAL = 15

	LOGDIR = "."

	# Model Constants
	IGNORE_INDEX = -100
	DEFAULT_IMAGE_TOKEN = "<image>"

	SENTINEL_TOKEN = "<vila/sentinel>"
	MEDIA_TOKENS = {
	"image": "<image>",
	"video": "<vila/video>",
	}
	# <image> <vila/video> <vila/sentinel>
	# TODO(ligeng): need to discuss with Zhijian for the following tokens for different models.
	"""
	151643: AddedToken("<\|endoftext\|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	151644: AddedToken("<\|im_start\|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	151645: AddedToken("<\|im_end\|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	151646: AddedToken("[BOS]", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	151647: AddedToken("[PAD]", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	151648: AddedToken("<vila/sentinel>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	151649: AddedToken("<image>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	151650: AddedToken("<vila/video>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	"""
	NUM_EXTRA_TOKENS = 8