Instructions to use mohsinshah/git-base-coco-dummy-temp12 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mohsinshah/git-base-coco-dummy-temp12 with Transformers:

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

pipe = pipeline("image-text-to-text", model="mohsinshah/git-base-coco-dummy-temp12")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("mohsinshah/git-base-coco-dummy-temp12")
model = AutoModelForMultimodalLM.from_pretrained("mohsinshah/git-base-coco-dummy-temp12", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mohsinshah/git-base-coco-dummy-temp12 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mohsinshah/git-base-coco-dummy-temp12"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mohsinshah/git-base-coco-dummy-temp12",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mohsinshah/git-base-coco-dummy-temp12

SGLang

How to use mohsinshah/git-base-coco-dummy-temp12 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 "mohsinshah/git-base-coco-dummy-temp12" \
    --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": "mohsinshah/git-base-coco-dummy-temp12",
		"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 "mohsinshah/git-base-coco-dummy-temp12" \
        --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": "mohsinshah/git-base-coco-dummy-temp12",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mohsinshah/git-base-coco-dummy-temp12 with Docker Model Runner:
```
docker model run hf.co/mohsinshah/git-base-coco-dummy-temp12
```

mohsinshah commited on Aug 11, 2023

Commit

a5d90be

1 Parent(s): 6c04cbc

Training in progress, step 450

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Aug11_05-44-24_gypsum-gpu187/events.out.tfevents.1691732672.gypsum-gpu187 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887d5cbbd13bffe9d18e742bd5db6959e8054c2a7783133ad20d925d159d7a9f
 size 706594713

 version https://git-lfs.github.com/spec/v1
+oid sha256:9811dbbb77e544b1ebf061e7197757203fefd55cd64381c44dc6afc42934fa42
 size 706594713

runs/Aug11_05-44-24_gypsum-gpu187/events.out.tfevents.1691732672.gypsum-gpu187 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be648de287f30ddef9075bde8e120e7da40d5c4dba7348e618eefe4fd27e2ca6
-size 10090

 version https://git-lfs.github.com/spec/v1
+oid sha256:84db1082fec863720ab125c8a2bf3088b0701446b92ad8c8d634b8bf9f9a0f39
+size 10571