Instructions to use mychen76/mistral7b_ocr_to_json_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mychen76/mistral7b_ocr_to_json_v1 with Transformers:

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

pipe = pipeline("text-generation", model="mychen76/mistral7b_ocr_to_json_v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mychen76/mistral7b_ocr_to_json_v1")
model = AutoModelForCausalLM.from_pretrained("mychen76/mistral7b_ocr_to_json_v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mychen76/mistral7b_ocr_to_json_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mychen76/mistral7b_ocr_to_json_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mychen76/mistral7b_ocr_to_json_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mychen76/mistral7b_ocr_to_json_v1

SGLang

How to use mychen76/mistral7b_ocr_to_json_v1 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 "mychen76/mistral7b_ocr_to_json_v1" \
    --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": "mychen76/mistral7b_ocr_to_json_v1",
		"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 "mychen76/mistral7b_ocr_to_json_v1" \
        --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": "mychen76/mistral7b_ocr_to_json_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mychen76/mistral7b_ocr_to_json_v1 with Docker Model Runner:
```
docker model run hf.co/mychen76/mistral7b_ocr_to_json_v1
```

Using the model

by TakMaz - opened Dec 6, 2023

Discussion

TakMaz

Dec 6, 2023

Hello,

when I pass in "Sale #: S1 -40 1206145922\nServed by Lewis A\nS1 -40 1206145922\nDescription\nAmount\nM&M's Chocolate\n£1.50\nSubtotal:\n£1.50\nTotal ex tax:\n- VAT\n£1.25\n£0.25\nTotal Inc Tax:\nMethod\nVisa\n£1.50\nAmount\n£1.50\nPrices shown in GBP\n2023-12-06 14:59:39\nRegister: Soho POS 1\nPrinter: Soho Works Shoreditch - POS 1-TM-m30_02\n7738\nSale ID: k3vvig7k\nVAT: 283 1918 86\n"

The model does not return an expected outcome i.e.

{ "receipt": { "store": "BAJA FRESH", "manager": "GENERAL MANAGER: NORMAN", "address": "176 Rosa C", "check": "Chk 7545", "date": "Dec26'0707:26PM", "tax": "Gst0", "total": "20.00", "payment": "CASH", "change": "0.61", "discount": "Discount on purchases of $5.00 or more,Offer expires in 30 day", "coupon": "Use this receipt as coupon", "survey": "Take our brief survey", "redemption": "Write down redemption code", "prompt": "When Prompted, Enter Store Write down redemption code Use this receipt as coupon", "items": [ { "name": "1 BAJA STEAK", "price": "6.95", "modifiers": [ "NO GUACAMOLE", "ENCHILADO STYLE" ] }, { "name": "TAKE OUT", "price": "1.49" } ] } }

I deployed this with AN API and it did not work, even with the special characters removed. What am I doing wrong?

Sohaib

Dec 22, 2023

can you share your code and input structure here?

mychen76

Owner Aug 1, 2024

please take a quick look on the sample usage notebooks below:

English Receipts

model_id="mychen76/mistral7b_ocr_to_json_v1"

https://github.com/minyang-chen/LLM_convert_receipt_image-to-json_or_xml/blob/main/Convert_Receipt_Image-to-Json_using_OCR_to_JSON_v1-English.ipynb

model_id: mychen76/mistral_ocr2json_v3_chatml

https://github.com/minyang-chen/LLM_convert_receipt_image-to-json_or_xml/blob/main/Convert_Receipt_Image-to-Json_using_OCR_to_JSON_v2_ChatML.ipynb
German Receipts

model_id="mychen76/mistral7b_ocr_to_json_v1"

Test01 https://github.com/minyang-chen/LLM_convert_receipt_image-to-json_or_xml/blob/main/Convert_Receipt_Image-to-Json_using_OCR_to_JSON_v1-German-Test1-passed.ipynb

Test02 https://github.com/minyang-chen/LLM_convert_receipt_image-to-json_or_xml/blob/main/Convert_Receipt_Image-to-Json_using_OCR_to_JSON_v1-German-Test2-failed.ipynb

Test03 https://github.com/minyang-chen/LLM_convert_receipt_image-to-json_or_xml/blob/main/Convert_Receipt_Image-to-Json_using_OCR_to_JSON_v1-German-Test3-okay.ipynb

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Using the model

English Receipts

https://github.com/minyang-chen/LLM_convert_receipt_image-to-json_or_xml/blob/main/Convert_Receipt_Image-to-Json_using_OCR_to_JSON_v2_ChatML.ipynbGerman Receipts

https://github.com/minyang-chen/LLM_convert_receipt_image-to-json_or_xml/blob/main/Convert_Receipt_Image-to-Json_using_OCR_to_JSON_v2_ChatML.ipynb
German Receipts