Instructions to use younsmirzai/stackadvisor-extractor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use younsmirzai/stackadvisor-extractor with Transformers:

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

pipe = pipeline("text-generation", model="younsmirzai/stackadvisor-extractor")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("younsmirzai/stackadvisor-extractor")
model = AutoModelForSeq2SeqLM.from_pretrained("younsmirzai/stackadvisor-extractor", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use younsmirzai/stackadvisor-extractor with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/younsmirzai/stackadvisor-extractor

SGLang

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

Docker Model Runner
How to use younsmirzai/stackadvisor-extractor with Docker Model Runner:
```
docker model run hf.co/younsmirzai/stackadvisor-extractor
```

younsmirzai commited on Jan 13

Commit

fe770e5

verified ·

1 Parent(s): 0589f5a

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +5 -17

README.md CHANGED Viewed

@@ -1,25 +1,13 @@
 ---
-pipeline_tag: text2text-generation
 tags:
 - t5
 - pytorch
-- text2text-generation
 ---
 # StackAdvisor Order Extractor
-T5-small model fine-tuned for extracting delivery order information from OCR text.
-## Usage
-```python
-from transformers import T5ForConditionalGeneration, T5Tokenizer
-model = T5ForConditionalGeneration.from_pretrained("younsmirzai/stackadvisor-extractor")
-tokenizer = T5Tokenizer.from_pretrained("younsmirzai/stackadvisor-extractor")
-text = "£6.04 2 orders Sainsbury's SA18JA Accept and go"
-inputs = tokenizer(text, return_tensors="pt", max_length=256, truncation=True)
-outputs = model.generate(**inputs, max_length=128)
-result = tokenizer.decode(outputs[0], skip_special_tokens=True)
-print(result)
-```

 ---
+language: en
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
 tags:
 - t5
 - pytorch
 ---
 # StackAdvisor Order Extractor
+T5-small model for extracting delivery order information from OCR text.