Instructions to use liuhaotian/LLaVA-7b-delta-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liuhaotian/LLaVA-7b-delta-v0 with Transformers:

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

pipe = pipeline("text-generation", model="liuhaotian/LLaVA-7b-delta-v0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liuhaotian/LLaVA-7b-delta-v0")
model = AutoModelForCausalLM.from_pretrained("liuhaotian/LLaVA-7b-delta-v0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liuhaotian/LLaVA-7b-delta-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liuhaotian/LLaVA-7b-delta-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/LLaVA-7b-delta-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liuhaotian/LLaVA-7b-delta-v0

SGLang

How to use liuhaotian/LLaVA-7b-delta-v0 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 "liuhaotian/LLaVA-7b-delta-v0" \
    --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": "liuhaotian/LLaVA-7b-delta-v0",
		"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 "liuhaotian/LLaVA-7b-delta-v0" \
        --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": "liuhaotian/LLaVA-7b-delta-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liuhaotian/LLaVA-7b-delta-v0 with Docker Model Runner:
```
docker model run hf.co/liuhaotian/LLaVA-7b-delta-v0
```

liuhaotian commited on Apr 30, 2023

Commit

82f0879

1 Parent(s): 318f11c

Update README.md

Browse files

Files changed (1) hide show

README.md +44 -0

README.md CHANGED Viewed

@@ -1,3 +1,47 @@
 ---
 license: apache-2.0
 ---

 ---
 license: apache-2.0
+inference: false
 ---
+**NOTE: This "delta model" cannot be used directly.**
+Users have to apply it on top of the original LLaMA weights to get actual LLaVA weights.
+See https://github.com/haotian-liu/LLaVA#llava-weights for instructions.
+<br>
+<br>
+# LLaVA Model Card
+## Model details
+**Model type:**
+LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data.
+It is an auto-regressive language model, based on the transformer architecture.
+**Model date:**
+LLaVA was trained in April 2023.
+**Paper or resources for more information:**
+https://llava-vl.github.io/
+**License:**
+Apache License 2.0
+**Where to send questions or comments about the model:**
+https://github.com/haotian-liu/LLaVA/issues
+## Intended use
+**Primary intended uses:**
+The primary use of LLaVA is research on large multimodal models and chatbots.
+**Primary intended users:**
+The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
+## Training dataset
+595K filtered image-text pairs from CC3M.
+150K GPT-generated multimodal instruction-following data.
+## Evaluation dataset
+A preliminary evaluation of the model quality is conducted by creating a set of 90 visual reasoning questions from 30 unique images randomly sampled from COCO val 2014 and each is associated with three types of questions: conversational, detailed description, and complex reasoning. We utilize GPT-4 to judge the model outputs.
+We also evaluate our model on the ScienceQA dataset.  Our synergy with GPT-4 sets a new state-of-the-art on the dataset.
+See https://llava-vl.github.io/ for more details.