Instructions to use venkateshtata/BLIP-finetuned-NICE-image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use venkateshtata/BLIP-finetuned-NICE-image-captioning with Transformers:

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

pipe = pipeline("image-text-to-text", model="venkateshtata/BLIP-finetuned-NICE-image-captioning")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("venkateshtata/BLIP-finetuned-NICE-image-captioning")
model = AutoModelForImageTextToText.from_pretrained("venkateshtata/BLIP-finetuned-NICE-image-captioning")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use venkateshtata/BLIP-finetuned-NICE-image-captioning with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/venkateshtata/BLIP-finetuned-NICE-image-captioning

SGLang

How to use venkateshtata/BLIP-finetuned-NICE-image-captioning 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 "venkateshtata/BLIP-finetuned-NICE-image-captioning" \
    --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": "venkateshtata/BLIP-finetuned-NICE-image-captioning",
		"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 "venkateshtata/BLIP-finetuned-NICE-image-captioning" \
        --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": "venkateshtata/BLIP-finetuned-NICE-image-captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use venkateshtata/BLIP-finetuned-NICE-image-captioning with Docker Model Runner:
```
docker model run hf.co/venkateshtata/BLIP-finetuned-NICE-image-captioning
```

venkateshtata commited on Jan 8, 2024

Commit

12ef6ba

1 Parent(s): 3e12503

Upload BlipForConditionalGeneration

Browse files

Files changed (3) hide show

config.json +31 -0
generation_config.json +7 -0
model.safetensors +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "_name_or_path": "Salesforce/blip-image-captioning-large",
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "encoder_hidden_size": 1024,
+    "initializer_factor": 1.0,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "blip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24
+  }
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 30522,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.0.dev0"
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e29feb71dc93b3c385d7256a4c188d2d84593caddc41e0fc73917536944fd249
+size 1879010480