mychen76 commited on
Commit
f82444b
1 Parent(s): 0b73710

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
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
  ```