ebadhussain20 commited on
Commit
e30dbf3
·
verified ·
1 Parent(s): 4e5d4b4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -16
README.md CHANGED
@@ -13,31 +13,50 @@ licence: license
13
  This model is a fine-tuned version of [unsloth/qwen2-vl-7b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen2-vl-7b-instruct-unsloth-bnb-4bit).
14
  It has been trained using [TRL](https://github.com/huggingface/trl).
15
 
16
- ## Quick start
 
 
 
 
 
17
 
18
- ```python
19
- from transformers import pipeline
20
 
21
- question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
22
- generator = pipeline("text-generation", model="None", device="cuda")
23
- output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
24
- print(output["generated_text"])
25
  ```
26
 
27
- ## Training procedure
 
 
 
 
 
 
 
 
 
 
 
 
28
 
29
-
30
 
 
31
 
32
- This model was trained with SFT.
33
 
34
- ### Framework versions
 
 
 
 
 
 
35
 
36
- - TRL: 0.24.0
37
- - Transformers: 5.5.0
38
- - Pytorch: 2.10.0+cu128
39
- - Datasets: 4.3.0
40
- - Tokenizers: 0.22.2
 
41
 
42
  ## Citations
43
 
 
13
  This model is a fine-tuned version of [unsloth/qwen2-vl-7b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen2-vl-7b-instruct-unsloth-bnb-4bit).
14
  It has been trained using [TRL](https://github.com/huggingface/trl).
15
 
16
+ ##A transformer-based OCR model fine-tuned for recognizing Urdu text from images.
17
+
18
+ This repository contains a fine-tuned VisionEncoderDecoderModel built on top of TrOCR for Urdu Optical Character Recognition (OCR). The model is trained to extract Urdu text from scanned documents, printed pages, and image-based text inputs.
19
+
20
+ Open model
21
+ View benchmark notebook
22
 
 
 
23
 
 
 
 
 
24
  ```
25
 
26
+ ## Highlights
27
+
28
+ Fine-tuned specifically for Urdu script recognition.
29
+
30
+ Works on scanned pages, screenshots, and cropped text regions.
31
+
32
+ Built using Hugging Face Transformers and TrOCR.
33
+
34
+ Easy inference pipeline with minimal code..
35
+
36
+ ### Quick Start
37
+
38
+ Install dependencies
39
 
40
+ Load the model
41
 
42
+ Run inference
43
 
44
+ ###Training Procedure
45
 
46
+ This model was fine-tuned using supervised learning on paired image–text data for Urdu OCR.
47
+ ###Training details
48
+ ###Parameter Value
49
+ Base model microsoft/trocr-base-handwritten
50
+ Task Sequence-to-sequence OCR
51
+ Framework Transformers Trainer API
52
+ Optimization Cross-entropy loss
53
 
54
+ ###Intended Use
55
+ ###Suitable for
56
+ Digitizing Urdu books and documents.
57
+ Extracting text from scanned PDFs.
58
+ OCR preprocessing for NLP pipelines.
59
+ Research and educational projects involving Urdu script.
60
 
61
  ## Citations
62