Instructions to use Humayoun/TrOCRTraining2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Humayoun/TrOCRTraining2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Humayoun/TrOCRTraining2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Humayoun/TrOCRTraining2")
model = AutoModelForMultimodalLM.from_pretrained("Humayoun/TrOCRTraining2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Humayoun/TrOCRTraining2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Humayoun/TrOCRTraining2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Humayoun/TrOCRTraining2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Humayoun/TrOCRTraining2

SGLang

How to use Humayoun/TrOCRTraining2 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 "Humayoun/TrOCRTraining2" \
    --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": "Humayoun/TrOCRTraining2",
		"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 "Humayoun/TrOCRTraining2" \
        --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": "Humayoun/TrOCRTraining2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Humayoun/TrOCRTraining2 with Docker Model Runner:
```
docker model run hf.co/Humayoun/TrOCRTraining2
```

Humayoun commited on May 9, 2023

Commit

7a8f4ad

1 Parent(s): 4b4f10e

Training in progress, epoch 9

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/May09_21-59-15_945d7895ffaf/events.out.tfevents.1683669917.945d7895ffaf.413.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00cf9f3c70bf066d69c8f888b01c3b013be12e0efd847bc492de1600f0081a92
 size 1539625673

 version https://git-lfs.github.com/spec/v1
+oid sha256:8aaecd849b8de5f54810bc6b28d750c2cbdc019b039f9cd784a85379c8af0d8d
 size 1539625673

runs/May09_21-59-15_945d7895ffaf/events.out.tfevents.1683669917.945d7895ffaf.413.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386f4cfca84cdd9cacdd4832fb05fff0f384b687ffe0d0d0358c755b7a0ba157
-size 39914

 version https://git-lfs.github.com/spec/v1
+oid sha256:5f433e1d5164a8ae19585b1a8a33cde66d1455b55d841b2222b213d728e5d192
+size 43843