Instructions to use Salesforce/blip2-opt-6.7b-coco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/blip2-opt-6.7b-coco with Transformers:

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

pipe = pipeline("image-text-to-text", model="Salesforce/blip2-opt-6.7b-coco")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Salesforce/blip2-opt-6.7b-coco")
model = AutoModelForMultimodalLM.from_pretrained("Salesforce/blip2-opt-6.7b-coco", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Salesforce/blip2-opt-6.7b-coco with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/blip2-opt-6.7b-coco"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/blip2-opt-6.7b-coco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/blip2-opt-6.7b-coco

SGLang

How to use Salesforce/blip2-opt-6.7b-coco 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 "Salesforce/blip2-opt-6.7b-coco" \
    --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": "Salesforce/blip2-opt-6.7b-coco",
		"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 "Salesforce/blip2-opt-6.7b-coco" \
        --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": "Salesforce/blip2-opt-6.7b-coco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/blip2-opt-6.7b-coco with Docker Model Runner:
```
docker model run hf.co/Salesforce/blip2-opt-6.7b-coco
```

blip2-opt-6.7b-coco / config.json

xurantju

Update for `transformers` (#3)

87ba9c6 verified almost 2 years ago

Raw

History Blame Contribute Delete

1.01 kB

	{
	"architectures": [
	"Blip2ForConditionalGeneration"
	],
	"image_text_hidden_size": 256,
	"image_token_index": 50265,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"model_type": "blip-2",
	"num_query_tokens": 32,
	"qformer_config": {
	"classifier_dropout": null,
	"model_type": "blip_2_qformer"
	},
	"text_config": {
	"activation_dropout": 0.0,
	"architectures": [
	"OPTForCausalLM"
	],
	"eos_token_id": 50118,
	"ffn_dim": 16384,
	"hidden_size": 4096,
	"model_type": "opt",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"prefix": "</s>",
	"torch_dtype": "float16",
	"vocab_size": 50304,
	"word_embed_proj_dim": 4096
	},
	"torch_dtype": "float32",
	"transformers_version": "4.47.0.dev0",
	"use_decoder_only_language_model": true,
	"vision_config": {
	"dropout": 0.0,
	"image_size": 364,
	"initializer_factor": 1.0,
	"model_type": "blip_2_vision_model",
	"num_channels": 3,
	"projection_dim": 512
	}
	}