Instructions to use leejuhyoeng/batch16_4e_5_blip with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leejuhyoeng/batch16_4e_5_blip with Transformers:

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

pipe = pipeline("image-text-to-text", model="leejuhyoeng/batch16_4e_5_blip")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("leejuhyoeng/batch16_4e_5_blip")
model = AutoModelForImageTextToText.from_pretrained("leejuhyoeng/batch16_4e_5_blip")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use leejuhyoeng/batch16_4e_5_blip with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leejuhyoeng/batch16_4e_5_blip"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leejuhyoeng/batch16_4e_5_blip",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/leejuhyoeng/batch16_4e_5_blip

SGLang

How to use leejuhyoeng/batch16_4e_5_blip 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 "leejuhyoeng/batch16_4e_5_blip" \
    --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": "leejuhyoeng/batch16_4e_5_blip",
		"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 "leejuhyoeng/batch16_4e_5_blip" \
        --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": "leejuhyoeng/batch16_4e_5_blip",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use leejuhyoeng/batch16_4e_5_blip with Docker Model Runner:
```
docker model run hf.co/leejuhyoeng/batch16_4e_5_blip
```

leejuhyoeng commited on Jan 26, 2024

Commit

ea36824

verified ·

1 Parent(s): 6d985f7

Training in progress, step 213

Browse files

Files changed (3) hide show

config.json +29 -0
model.safetensors +3 -0
training_args.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "_name_or_path": "Salesforce/blip-image-captioning-base",
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "decoder_start_token_id": 101,
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "logit_scale_init_value": 2.6592,
+  "max_length": 50,
+  "model_type": "blip",
+  "pad_token_id": 0,
+  "projection_dim": 512,
+  "text_config": {
+    "initializer_factor": 1.0,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "model_type": "blip_vision_model",
+    "num_channels": 3
+  }
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3cc048a345783f1764efd5a6a54173494d3e745559d81e4029137230c0bdbd
+size 989717056

training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef428d2491921efffd5cfc9ebe86644b8416b7df0e4e27e164024e3cc975a3d
+size 4664