Instructions to use jaimin/git-base-image_cap with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jaimin/git-base-image_cap with Transformers:

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

pipe = pipeline("image-text-to-text", model="jaimin/git-base-image_cap")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("jaimin/git-base-image_cap")
model = AutoModelForImageTextToText.from_pretrained("jaimin/git-base-image_cap")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jaimin/git-base-image_cap with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jaimin/git-base-image_cap

SGLang

How to use jaimin/git-base-image_cap 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 "jaimin/git-base-image_cap" \
    --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": "jaimin/git-base-image_cap",
		"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 "jaimin/git-base-image_cap" \
        --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": "jaimin/git-base-image_cap",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jaimin/git-base-image_cap with Docker Model Runner:
```
docker model run hf.co/jaimin/git-base-image_cap
```

jaimin commited on Mar 20, 2023

Commit

4cadab5

1 Parent(s): 8a713a4

Training in progress, epoch 1

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Mar20_15-43-03_e000dbfeea14/events.out.tfevents.1679327002.e000dbfeea14.18609.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e68a7830e9724833f1f8877497e5f0b24aa07e7deae646ac3c88eff34cb4f7e
 size 706594713

 version https://git-lfs.github.com/spec/v1
+oid sha256:1257cfc953f71679189ff1d58cd85848f36a180539ed884e9cfdec6f0715170e
 size 706594713

runs/Mar20_15-43-03_e000dbfeea14/events.out.tfevents.1679327002.e000dbfeea14.18609.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cede6893033bbb6a9c93f8f337a73d7fc8c82cf0165bb124c5517e208d944bfb
-size 6177

 version https://git-lfs.github.com/spec/v1
+oid sha256:0d8e54d29d9d242cf2fdeabccef774625811c1003a01d1f6a53971ee3244814b
+size 6331