Instructions to use mychen76/mistral_ocr2json_v3_chatml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mychen76/mistral_ocr2json_v3_chatml with Transformers:

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

pipe = pipeline("text-generation", model="mychen76/mistral_ocr2json_v3_chatml")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mychen76/mistral_ocr2json_v3_chatml")
model = AutoModelForCausalLM.from_pretrained("mychen76/mistral_ocr2json_v3_chatml")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mychen76/mistral_ocr2json_v3_chatml with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mychen76/mistral_ocr2json_v3_chatml"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mychen76/mistral_ocr2json_v3_chatml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mychen76/mistral_ocr2json_v3_chatml

SGLang

How to use mychen76/mistral_ocr2json_v3_chatml 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/mistral_ocr2json_v3_chatml" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mychen76/mistral_ocr2json_v3_chatml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/mistral_ocr2json_v3_chatml" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mychen76/mistral_ocr2json_v3_chatml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mychen76/mistral_ocr2json_v3_chatml with Docker Model Runner:
```
docker model run hf.co/mychen76/mistral_ocr2json_v3_chatml
```

Format

chatml

Usage Notebook

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

receipt_boxes from Paddle-OCR

ocr boxes:

[
    [[[188.0, 54.0], [453.0, 54.0], [453.0, 85.0], [188.0, 85.0]], ('The Lone Pine', 0.9998102188110352)],
    [[[194.0, 96.0], [449.0, 98.0], [449.0, 122.0], [194.0, 120.0]], ('43 Manchester Road', 0.9988968372344971)],
    [[[228.0, 127.0], [416.0, 130.0], [416.0, 154.0], [228.0, 151.0]], ('12480 Brisbane', 0.9658010601997375)],
    [[[267.0, 162.0], [375.0, 162.0], [375.0, 186.0], [267.0, 186.0]], ('Australia', 0.9997145533561707)],
    [[[234.0, 193.0], [409.0, 193.0], [409.0, 216.0], [234.0, 216.0]], ('617-3236-6207', 0.9996874332427979)],
    [[[46.0, 255.0], [308.0, 255.0], [308.0, 278.0], [46.0, 278.0]], ('Invoice 08000008', 0.9919923543930054)],
    [[[466.0, 255.0], [598.0, 255.0], [598.0, 278.0], [466.0, 278.0]], ('09/04/08', 0.9994747042655945)],
    [[[42.0, 283.0], [132.0, 283.0], [132.0, 311.0], [42.0, 311.0]], ('Table', 0.9969210624694824)],
    [[[174.0, 283.0], [214.0, 283.0], [214.0, 311.0], [174.0, 311.0]], ('25', 0.9997891783714294)],
    [[[514.0, 284.0], [601.0, 284.0], [601.0, 311.0], [514.0, 311.0]], ('12:45', 0.9964954257011414)],
    [[[67.0, 346.0], [291.0, 349.0], [291.0, 376.0], [67.0, 374.0]], ('2 Carlsberg Bottle', 0.9987921118736267)],
    [[[515.0, 346.0], [599.0, 346.0], [599.0, 372.0], [515.0, 372.0]], ('16.00', 0.9999278783798218)],
    [
        [[69.0, 385.0], [395.0, 387.0], [395.0, 411.0], [69.0, 409.0]],
        ('3 Heineken Draft Standard.', 0.9832896590232849)
    ],
    [[[515.0, 384.0], [599.0, 384.0], [599.0, 409.0], [515.0, 409.0]], ('24.60', 0.9998160600662231)],
    [
        [[71.0, 423.0], [391.0, 423.0], [391.0, 446.0], [71.0, 446.0]],
        ('1 Heineken Draft Half Liter.', 0.9641079306602478)
    ],
    [[[515.0, 421.0], [601.0, 421.0], [601.0, 450.0], [515.0, 450.0]], ('15.20', 0.9998868703842163)],
    [
        [[69.0, 460.0], [430.0, 461.0], [430.0, 485.0], [69.0, 484.0]],
        ('2 Carlsberg Bucket (5 bottles).', 0.974445641040802)
    ],
    [[[515.0, 461.0], [599.0, 461.0], [599.0, 486.0], [515.0, 486.0]], ('80.00', 0.9999423027038574)],
    [
        [[69.0, 498.0], [367.0, 500.0], [367.0, 524.0], [69.0, 522.0]],
        ('4 Grilled Chicken Breast.', 0.9773013591766357)
    ],
    [[[515.0, 499.0], [599.0, 499.0], [599.0, 524.0], [515.0, 524.0]], ('74.00', 0.9999669194221497)],
    [[[68.0, 534.0], [250.0, 537.0], [250.0, 562.0], [68.0, 560.0]], ('3 Sirloin Steak', 0.9997309446334839)],
    [[[515.0, 537.0], [599.0, 537.0], [599.0, 561.0], [515.0, 561.0]], ('96.00', 0.9999544024467468)],
    [[[67.0, 571.0], [162.0, 574.0], [161.0, 601.0], [67.0, 598.0]], ('1 Coke', 0.9997830390930176)],
    [[[530.0, 572.0], [602.0, 572.0], [602.0, 601.0], [530.0, 601.0]], ('3.50', 0.9999455213546753)],
    [[[69.0, 609.0], [219.0, 613.0], [218.0, 638.0], [68.0, 634.0]], ('5 Ice Cream', 0.9914276003837585)],
    [[[516.0, 611.0], [599.0, 611.0], [599.0, 637.0], [516.0, 637.0]], ('18.00', 0.9999335408210754)],
    [[[154.0, 664.0], [288.0, 664.0], [288.0, 688.0], [154.0, 688.0]], ('Subtotal', 0.9990750551223755)],
    [[[499.0, 664.0], [599.0, 664.0], [599.0, 688.0], [499.0, 688.0]], ('327.30', 0.9999768137931824)],
    [
        [[155.0, 701.0], [397.0, 701.0], [397.0, 724.0], [155.0, 724.0]],
        ('Sales/Gov Tax - 5%', 0.9552016854286194)
    ],
    [[[514.0, 697.0], [601.0, 697.0], [601.0, 724.0], [514.0, 724.0]], ('16.36', 0.999823272228241)],
    [
        [[155.0, 733.0], [419.0, 733.0], [419.0, 757.0], [155.0, 757.0]],
        ('Service Charge - 10%', 0.9921379089355469)
    ],
    [[[512.0, 728.0], [601.0, 731.0], [600.0, 759.0], [511.0, 757.0]], ('32.73', 0.9999620318412781)],
    [[[154.0, 775.0], [335.0, 775.0], [335.0, 799.0], [154.0, 799.0]], ('GRAND TOTAL', 0.9899482131004333)],
    [[[499.0, 778.0], [599.0, 778.0], [599.0, 802.0], [499.0, 802.0]], ('376.40', 0.9999797940254211)],
    [[[39.0, 831.0], [223.0, 831.0], [223.0, 859.0], [39.0, 859.0]], ('Thank you and', 0.9922393560409546)],
    [[[336.0, 831.0], [407.0, 831.0], [407.0, 860.0], [336.0, 860.0]], ('Cash', 0.9998616576194763)],
    [[[499.0, 831.0], [601.0, 831.0], [601.0, 859.0], [499.0, 859.0]], ('400.00', 0.9998554587364197)],
    [[[38.0, 866.0], [220.0, 862.0], [220.0, 891.0], [38.0, 895.0]], ('see you again!', 0.9798372983932495)],
    [[[336.0, 864.0], [438.0, 869.0], [437.0, 898.0], [335.0, 894.0]], ('Change', 0.9998979568481445)],
    [[[515.0, 867.0], [599.0, 867.0], [599.0, 892.0], [515.0, 892.0]], ('23.60', 0.9999337196350098)],
    [[[37.0, 901.0], [108.0, 901.0], [108.0, 930.0], [37.0, 930.0]], ('John', 0.9990785717964172)],
    [
        [[73.0, 962.0], [569.0, 965.0], [569.0, 991.0], [73.0, 989.0]],
        ('Bring this bill back within the next 10 days', 0.9880552887916565)
    ],
    [
        [[50.0, 1000.0], [591.0, 1000.0], [591.0, 1023.0], [50.0, 1023.0]],
        ("and get 15% discount on that day's food bill..", 0.9851154685020447)
    ]
]

prompt

f"""<|im_start|>system You are POS receipt data expert, parse, detect, recognize and convert following receipt OCR image result into structure receipt data object. Don't make up value not in the Input. Output must be a well-formed JSON object.```json<|im_end|> <|im_start|>user {receipt_boxes}<|im_end|> <|im_start|>assistant """

Result

<|im_start|>assistant
{
  "store_name": "The Lone Pine",
  "store_address": "43 Manchester Road",
  "city": "Brisbane",
  "country": "Australia",
  "phone": "617-3236-6207",
  "invoice_number": "08000008",
  "invoice_date": "09/04/08",
  "table_number": "25",
  "time": "12:45",
  "items": [
    {
      "item_name": "Carlsberg Bottle",
      "quantity": "2",
      "price": "16.00"
    },
    {
      "item_name": "Heineken Draft Half Liter.",
      "quantity": "1",
      "price": "15.20"
    },
    {
      "item_name": "Heineken Draft Standard.",
      "quantity": "3",
      "price": "12.00"
    },
    {
      "item_name": "Sirloin Steak",
      "quantity": "3",
      "price": "96.00"
    },
    {
      "item_name": "Grilled Chicken Breast",
      "quantity": "4",
      "price": "74.00"
    },
    {
      "item_name": "Coke",
      "quantity": "1",
      "price": "3.50"
    },
    {
      "item_name": "Ice Cream",
      "quantity": "5",
      "price": "18.00"
    }
  ],
  "subtotal": "327.30",
  "tax": "16.36",
  "service_charge": "32.73",
  "total": "376.40",
  "payment": {
    "cash": "400.00",
    "change": "23.60"
  },
  "customer": {
    "name": "John"
  },
  "discount": "15%"
}<|im_end|></s>

Uploaded model

Developed by: mychen76
License: apache-2.0
Finetuned from model : unsloth/mistral-7b-instruct-v0.2-bnb-4bit

Downloads last month: 6

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for mychen76/mistral_ocr2json_v3_chatml

Base model

unsloth/mistral-7b-instruct-v0.2-bnb-4bit

Finetuned

(503)

this model

Collection including mychen76/mistral_ocr2json_v3_chatml

Receipt & Invoices

Collection

13 items • Updated Mar 2 • 13