Instructions to use ChiJuiChen/GenerativeImage2Text-naruto with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChiJuiChen/GenerativeImage2Text-naruto with Transformers:

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

pipe = pipeline("image-text-to-text", model="ChiJuiChen/GenerativeImage2Text-naruto")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("ChiJuiChen/GenerativeImage2Text-naruto")
model = AutoModelForImageTextToText.from_pretrained("ChiJuiChen/GenerativeImage2Text-naruto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ChiJuiChen/GenerativeImage2Text-naruto with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChiJuiChen/GenerativeImage2Text-naruto"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChiJuiChen/GenerativeImage2Text-naruto",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ChiJuiChen/GenerativeImage2Text-naruto

SGLang

How to use ChiJuiChen/GenerativeImage2Text-naruto 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 "ChiJuiChen/GenerativeImage2Text-naruto" \
    --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": "ChiJuiChen/GenerativeImage2Text-naruto",
		"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 "ChiJuiChen/GenerativeImage2Text-naruto" \
        --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": "ChiJuiChen/GenerativeImage2Text-naruto",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ChiJuiChen/GenerativeImage2Text-naruto with Docker Model Runner:
```
docker model run hf.co/ChiJuiChen/GenerativeImage2Text-naruto
```

ChiJuiChen commited on May 30, 2024

Commit

f6d0b78

verified ·

1 Parent(s): 9b82740

Training in progress, step 50

Browse files

Files changed (10) hide show

config.json +1 -1
model.safetensors +1 -1
runs/May30_13-06-18_pcslab-MS-7A69/events.out.tfevents.1717045581.pcslab-MS-7A69.62372.0 +3 -0
runs/May30_13-07-47_pcslab-MS-7A69/events.out.tfevents.1717045675.pcslab-MS-7A69.62372.1 +3 -0
runs/May30_13-09-18_pcslab-MS-7A69/events.out.tfevents.1717045760.pcslab-MS-7A69.62372.2 +3 -0
runs/May30_13-11-24_pcslab-MS-7A69/events.out.tfevents.1717045885.pcslab-MS-7A69.62732.0 +3 -0
runs/May30_13-12-25_pcslab-MS-7A69/events.out.tfevents.1717045949.pcslab-MS-7A69.62732.1 +3 -0
runs/May30_13-13-44_pcslab-MS-7A69/events.out.tfevents.1717046025.pcslab-MS-7A69.62900.0 +3 -0
runs/May30_13-35-40_pcslab-MS-7A69/events.out.tfevents.1717047340.pcslab-MS-7A69.63271.0 +3 -0
training_args.bin +1 -1

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/git-base",
   "architectures": [
     "GitForCausalLM"
   ],

 {
+  "_name_or_path": "ChiJuiChen/GenerativeImage2Text-naruto",
   "architectures": [
     "GitForCausalLM"
   ],

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368abed992a2acac0c56db914972556d369cef6cbf3c22341f93d5a14f034d88
 size 706516040

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb6b136fe8d796a5c6321dd8e2a6bf5fd8663b307df0be7670ed76a3fd5506d
 size 5048

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0db29a6461050aebf359b506153f2216072c60fcdc708938a03067a66f1580a
+size 5188

+version https://git-lfs.github.com/spec/v1
+oid sha256:be51b8bd4724af8181158471080b3f96f189ef3d39957b54ea807965b63e32f0
+size 5506

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

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

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

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