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

Libraries

How to use rasoulasadian/trocr_decoder_scratch with Transformers:

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

pipe = pipeline("image-text-to-text", model="rasoulasadian/trocr_decoder_scratch", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("rasoulasadian/trocr_decoder_scratch")
model = AutoModelForMultimodalLM.from_pretrained("rasoulasadian/trocr_decoder_scratch", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rasoulasadian/trocr_decoder_scratch with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rasoulasadian/trocr_decoder_scratch

SGLang

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

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

rasoulasadian commited on Apr 1, 2024

Commit

44a898c

verified ·

1 Parent(s): 1aa946e

Training in progress, epoch 8

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Apr01_00-14-34_6057e31535da/events.out.tfevents.1711930480.6057e31535da.157.1 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b9b521912ce4c0e9a2fb11e6e84ad1d81314a6b015d65eae75409812340d17
 size 114140760

 version https://git-lfs.github.com/spec/v1
+oid sha256:bea4ea6f7c54327b916da042578cc3e9ab77439bbc1008cb85636c43db92e071
 size 114140760

runs/Apr01_00-14-34_6057e31535da/events.out.tfevents.1711930480.6057e31535da.157.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706ab62766d9479a77ae512ecbd91ccd914eddb1d83bc5255f23ead3cf164259
-size 11402

 version https://git-lfs.github.com/spec/v1
+oid sha256:7144c07a303b6b1888f777618ab9b1e101953693ebc9fd43c979a3e3bdd0939e
+size 12989