Instructions to use rkdeva/BLIP-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rkdeva/BLIP-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="rkdeva/BLIP-1")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("rkdeva/BLIP-1") model = AutoModelForImageTextToText.from_pretrained("rkdeva/BLIP-1") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use rkdeva/BLIP-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rkdeva/BLIP-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rkdeva/BLIP-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rkdeva/BLIP-1
- SGLang
How to use rkdeva/BLIP-1 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 "rkdeva/BLIP-1" \ --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": "rkdeva/BLIP-1", "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 "rkdeva/BLIP-1" \ --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": "rkdeva/BLIP-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rkdeva/BLIP-1 with Docker Model Runner:
docker model run hf.co/rkdeva/BLIP-1
Upload BlipForConditionalGeneration
Browse files- config.json +26 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Salesforce/blip-image-captioning-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BlipForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"image_text_hidden_size": 256,
|
| 7 |
+
"initializer_factor": 1.0,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"logit_scale_init_value": 2.6592,
|
| 10 |
+
"model_type": "blip",
|
| 11 |
+
"projection_dim": 512,
|
| 12 |
+
"text_config": {
|
| 13 |
+
"initializer_factor": 1.0,
|
| 14 |
+
"model_type": "blip_text_model",
|
| 15 |
+
"num_attention_heads": 12
|
| 16 |
+
},
|
| 17 |
+
"torch_dtype": "float32",
|
| 18 |
+
"transformers_version": "4.34.1",
|
| 19 |
+
"vision_config": {
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"initializer_factor": 1.0,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"model_type": "blip_vision_model",
|
| 24 |
+
"num_channels": 3
|
| 25 |
+
}
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 30522,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.34.1"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc012ed24d6bbfe4de3cf406a0aa27955bfb1d8ac390e5eaf52ea95e8d6086cd
|
| 3 |
+
size 994578282
|