Update README.md
Browse files
README.md
CHANGED
@@ -2,36 +2,29 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: pszemraj/MiniLMv2-L6-H384_R-fineweb-100k
|
4 |
tags:
|
5 |
-
-
|
|
|
|
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
-
|
9 |
-
-
|
10 |
-
|
|
|
11 |
---
|
12 |
|
13 |
-
|
14 |
-
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
|
17 |
-
|
18 |
-
This model is a fine-tuned version of [pszemraj/MiniLMv2-L6-H384_R-fineweb-100k](https://huggingface.co/pszemraj/MiniLMv2-L6-H384_R-fineweb-100k) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.0162
|
21 |
- Accuracy: 0.996
|
22 |
- Num Input Tokens Seen: 61536256
|
23 |
|
24 |
-
## Model description
|
25 |
-
|
26 |
-
More information needed
|
27 |
|
28 |
## Intended uses & limitations
|
29 |
|
30 |
-
|
31 |
-
|
32 |
-
## Training and evaluation data
|
33 |
-
|
34 |
-
More information needed
|
35 |
|
36 |
## Training procedure
|
37 |
|
@@ -67,4 +60,4 @@ The following hyperparameters were used during training:
|
|
67 |
- Transformers 4.40.2
|
68 |
- Pytorch 2.2.0+cu121
|
69 |
- Datasets 2.19.1
|
70 |
-
- Tokenizers 0.19.1
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: pszemraj/MiniLMv2-L6-H384_R-fineweb-100k
|
4 |
tags:
|
5 |
+
- data processing
|
6 |
+
- data filter
|
7 |
+
- text quality
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
+
datasets:
|
11 |
+
- pszemraj/OCR-quality-classification
|
12 |
+
language:
|
13 |
+
- en
|
14 |
---
|
15 |
|
16 |
+
# MiniLMv2-L6-H384_R-OCR-quality
|
|
|
17 |
|
18 |
+
This model is a fine-tuned version of [pszemraj/MiniLMv2-L6-H384_R-fineweb-100k](https://hf.co/pszemraj/MiniLMv2-L6-H384_R-fineweb-100k) on `pszemraj/OCR-quality-classification`
|
|
|
|
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.0162
|
21 |
- Accuracy: 0.996
|
22 |
- Num Input Tokens Seen: 61536256
|
23 |
|
|
|
|
|
|
|
24 |
|
25 |
## Intended uses & limitations
|
26 |
|
27 |
+
predict whether a document is clean or noisy
|
|
|
|
|
|
|
|
|
28 |
|
29 |
## Training procedure
|
30 |
|
|
|
60 |
- Transformers 4.40.2
|
61 |
- Pytorch 2.2.0+cu121
|
62 |
- Datasets 2.19.1
|
63 |
+
- Tokenizers 0.19.1
|