Instructions to use HamAndCheese82/math_ocr_donut_temp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HamAndCheese82/math_ocr_donut_temp with Transformers:

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

pipe = pipeline("image-text-to-text", model="HamAndCheese82/math_ocr_donut_temp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("HamAndCheese82/math_ocr_donut_temp")
model = AutoModelForMultimodalLM.from_pretrained("HamAndCheese82/math_ocr_donut_temp", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HamAndCheese82/math_ocr_donut_temp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HamAndCheese82/math_ocr_donut_temp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HamAndCheese82/math_ocr_donut_temp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HamAndCheese82/math_ocr_donut_temp

SGLang

How to use HamAndCheese82/math_ocr_donut_temp 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 "HamAndCheese82/math_ocr_donut_temp" \
    --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": "HamAndCheese82/math_ocr_donut_temp",
		"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 "HamAndCheese82/math_ocr_donut_temp" \
        --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": "HamAndCheese82/math_ocr_donut_temp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HamAndCheese82/math_ocr_donut_temp with Docker Model Runner:
```
docker model run hf.co/HamAndCheese82/math_ocr_donut_temp
```

HamAndCheese82 commited on Apr 5, 2024

Commit

68b89d4

verified ·

1 Parent(s): 8680b7d

On validation process, epoch 0, global step 4

Browse files

Files changed (2) hide show

README.md +1 -0
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -4,6 +4,7 @@ tags:
 - validation_1
 - validation_2
 - validation_3
 ---
 # Model Card for Model ID

 - validation_1
 - validation_2
 - validation_3
+- validation_4
 ---
 # Model Card for Model ID

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a67c48b8301c817f68b757bc282063694c292a29e9fb69cef6e1aa6bbc05fc9c
 size 809099416

 version https://git-lfs.github.com/spec/v1
+oid sha256:9d2b4fa730cde5e9d17becf888b33b27810b5bc4be3594a5f898a7f56b94af93
 size 809099416