Instructions to use Tamazight/TrOCR-Tifinagh-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tamazight/TrOCR-Tifinagh-Small with Transformers:

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

pipe = pipeline("image-text-to-text", model="Tamazight/TrOCR-Tifinagh-Small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("Tamazight/TrOCR-Tifinagh-Small")
model = AutoModelForImageTextToText.from_pretrained("Tamazight/TrOCR-Tifinagh-Small")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tamazight/TrOCR-Tifinagh-Small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Tamazight/TrOCR-Tifinagh-Small

SGLang

How to use Tamazight/TrOCR-Tifinagh-Small 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 "Tamazight/TrOCR-Tifinagh-Small" \
    --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": "Tamazight/TrOCR-Tifinagh-Small",
		"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 "Tamazight/TrOCR-Tifinagh-Small" \
        --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": "Tamazight/TrOCR-Tifinagh-Small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tamazight/TrOCR-Tifinagh-Small with Docker Model Runner:
```
docker model run hf.co/Tamazight/TrOCR-Tifinagh-Small
```

Akseltinfat commited on 11 days ago

Commit

f388306

verified ·

1 Parent(s): 6b7196e

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -1

README.md CHANGED Viewed

@@ -1,6 +1,15 @@
 ---
 library_name: transformers
-tags: []
 ---
 # Model Card for Model ID

 ---
 library_name: transformers
+language:
+- zgh
+- tzm
+- shi
+license: apache-2.0
+datasets:
+- Tamazight/Tifinagh-OCR-39K
+base_model:
+- microsoft/trocr-small-printed
+pipeline_tag: image-text-to-text
 ---
 # Model Card for Model ID