Instructions to use Rodr16020/trocr_handwriten_cursive_text_detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rodr16020/trocr_handwriten_cursive_text_detection with Transformers:

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

pipe = pipeline("image-text-to-text", model="Rodr16020/trocr_handwriten_cursive_text_detection")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Rodr16020/trocr_handwriten_cursive_text_detection")
model = AutoModelForMultimodalLM.from_pretrained("Rodr16020/trocr_handwriten_cursive_text_detection")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rodr16020/trocr_handwriten_cursive_text_detection with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rodr16020/trocr_handwriten_cursive_text_detection"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rodr16020/trocr_handwriten_cursive_text_detection",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Rodr16020/trocr_handwriten_cursive_text_detection

SGLang

How to use Rodr16020/trocr_handwriten_cursive_text_detection 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 "Rodr16020/trocr_handwriten_cursive_text_detection" \
    --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": "Rodr16020/trocr_handwriten_cursive_text_detection",
		"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 "Rodr16020/trocr_handwriten_cursive_text_detection" \
        --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": "Rodr16020/trocr_handwriten_cursive_text_detection",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rodr16020/trocr_handwriten_cursive_text_detection with Docker Model Runner:
```
docker model run hf.co/Rodr16020/trocr_handwriten_cursive_text_detection
```

Rodr16020 commited on Oct 22, 2024

Commit

692a24e

verified ·

1 Parent(s): 2e44ffa

Finetuned V2 with more and curated data

Browse files

Files changed (3) hide show

preprocessor_config.json +0 -14
tokenizer.json +0 -0
tokenizer_config.json +0 -1

preprocessor_config.json CHANGED Viewed

@@ -1,18 +1,4 @@
 {
-  "_valid_processor_keys": [
-    "images",
-    "do_resize",
-    "size",
-    "resample",
-    "do_rescale",
-    "rescale_factor",
-    "do_normalize",
-    "image_mean",
-    "image_std",
-    "return_tensors",
-    "data_format",
-    "input_data_format"
-  ],
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,

 {
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -45,7 +45,6 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
-  "device_map": "cuda:1",
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",

   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",