Update README.md
Browse files
README.md
CHANGED
@@ -12,14 +12,17 @@ metrics:
|
|
12 |
- metric2
|
13 |
---
|
14 |
|
15 |
-
Model Architecture
|
|
|
16 |
The mychen76/mistral7b_ocr_to_json_v1 (LLM) is a finetuned for convert OCR text to Json object task. this experimental model is based on Mistral-7B-v0.1 which outperforms Llama 2 13B on all benchmarks tested.
|
17 |
|
18 |
-
Motivation
|
|
|
19 |
current OCR engines are well tested on image detection and text recognition. LLM model are well train for text process and generation.
|
20 |
Hence, leveraging output from OCR engine could save LLM training time for image-to-text use case such as invoice or receipt image to json object convertion task.
|
21 |
|
22 |
Model Usage:
|
|
|
23 |
Take a random receipt image picture, perform Image OCR to get text boxes then feed into LLM model to generate as well-pformed receipt json object.
|
24 |
|
25 |
```
|
|
|
12 |
- metric2
|
13 |
---
|
14 |
|
15 |
+
Model Architecture:
|
16 |
+
|
17 |
The mychen76/mistral7b_ocr_to_json_v1 (LLM) is a finetuned for convert OCR text to Json object task. this experimental model is based on Mistral-7B-v0.1 which outperforms Llama 2 13B on all benchmarks tested.
|
18 |
|
19 |
+
Motivation:
|
20 |
+
|
21 |
current OCR engines are well tested on image detection and text recognition. LLM model are well train for text process and generation.
|
22 |
Hence, leveraging output from OCR engine could save LLM training time for image-to-text use case such as invoice or receipt image to json object convertion task.
|
23 |
|
24 |
Model Usage:
|
25 |
+
|
26 |
Take a random receipt image picture, perform Image OCR to get text boxes then feed into LLM model to generate as well-pformed receipt json object.
|
27 |
|
28 |
```
|