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")

Inference
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
```

extract DOB

by kamrandar - opened May 22, 2024

Discussion

kamrandar

May 22, 2024

i want to promt the model to include in json file 'dob' that has been extracted by my 'OCR; which is in 'custom format' you can see my data is like this "text only:

wate Sale aratin fren aS 08436/00048
S.No. SSE/2007/ CENTRAL BOARD OF SECONDARY EDUCATION
151415 7 iii MARKS STATEMENT
Wve weet Wier, 2007
A ri
LL INDIA oe CONDARY SCHOOL EXAMINATION, 2007
ATH Neme AASHISH RANJAN STTPATS RollNe. Si BASS9

Sisil ST ATA Mother's Name PRATIMA KUMARI

| eT I ATS Father's Name ARUN KUMAR

SA FART Date of Birth ISTH AUGUST NINETEEN HUNDRED NINETY ONE
(eTeTS Schoo! OB4R6 SAINIK SCHOOL PURULIA WEST BENGAL

3 Whi MARKS OBTAINED
fsa SUBJECT

fer. | Weta} ala a ere) 9
TH | PR/IA | TOTAL TOTAL IN WORDS
ENGLISH COMM.

EIGHTY SIX
HINDI COURSE-B NINETY
MATHEMATICS NINETY SEVEN
SCIENCE & TECH. EIGHTY FOUR
PRAC.-INTERNAL 018
PRAC.-SKILLS EXT 018
SOCIAL SCIENCE

feria as

SEVENTY FIVE

AB : va A erqahVG Absent in the Subject uhvTa Result FASS

PR:3arTSs Practical o—~

IA : siaRa YeaieT Internal Assessment (Mohar 4
fRe* Delhi uven Pris

RATS Dated 27—-05~—-200T Controlier of Examinations

Scanned by CamScanner
"

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