Update README.md
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ This model is a fine-tuned version of [KT-AI/midm-bitext-S-7B-inst-v1](https://h
|
|
17 |
|
18 |
## Model description
|
19 |
|
20 |
-
KT-midm modelμ nsmcλ°μ΄ν°λ₯Ό νμ©νμ¬ λ―ΈμΈνλν λͺ¨λΈ
|
21 |
μν 리뷰 λ°μ΄ν°λ₯Ό κΈ°λ°μΌλ‘ μ¬μ©μκ° μμ±ν 리뷰μ κΈμ λλ λΆμ μ νμ
νλ€.
|
22 |
|
23 |
## Intended uses & limitations
|
@@ -27,13 +27,11 @@ KT-midm modelμ nsmcλ°μ΄ν°λ₯Ό νμ©νμ¬ λ―ΈμΈνλν λͺ¨λΈ
|
|
27 |
|
28 |
### Limitaions
|
29 |
μν 리뷰μ νΉνλμ΄ μμΌλ©°, λ€λ₯Έ μ νμλ μ νμ΄ μμ μ μμ
|
30 |
-
|
31 |
Colab T4 GPUμμ ν
μ€νΈ λμμ
|
32 |
|
33 |
## Training and evaluation data
|
34 |
|
35 |
Training data: nsmc 'train' data μ€ μμ 2000κ°μ μν
|
36 |
-
|
37 |
Evaluation data: nsmc 'test' data μ€ μμ 1000κ°μ μν
|
38 |
|
39 |
## Training procedure
|
@@ -56,7 +54,7 @@ The following hyperparameters were used during training:
|
|
56 |
### Training results
|
57 |
|
58 |
### μ νλ
|
59 |
-
Midm: μ νλ 0.89
|
60 |
| | Positive Prediction(PP) | Negative Prediction(NP) |
|
61 |
|--------------------|---------------------|---------------------|
|
62 |
| True Positive (TP) | 474 | 34 |
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
20 |
+
KT-midm modelμ nsmcλ°μ΄ν°λ₯Ό νμ©νμ¬ λ―ΈμΈνλν λͺ¨λΈ
|
21 |
μν 리뷰 λ°μ΄ν°λ₯Ό κΈ°λ°μΌλ‘ μ¬μ©μκ° μμ±ν 리뷰μ κΈμ λλ λΆμ μ νμ
νλ€.
|
22 |
|
23 |
## Intended uses & limitations
|
|
|
27 |
|
28 |
### Limitaions
|
29 |
μν 리뷰μ νΉνλμ΄ μμΌλ©°, λ€λ₯Έ μ νμλ μ νμ΄ μμ μ μμ
|
|
|
30 |
Colab T4 GPUμμ ν
μ€νΈ λμμ
|
31 |
|
32 |
## Training and evaluation data
|
33 |
|
34 |
Training data: nsmc 'train' data μ€ μμ 2000κ°μ μν
|
|
|
35 |
Evaluation data: nsmc 'test' data μ€ μμ 1000κ°μ μν
|
36 |
|
37 |
## Training procedure
|
|
|
54 |
### Training results
|
55 |
|
56 |
### μ νλ
|
57 |
+
Midm: μ νλ 0.89
|
58 |
| | Positive Prediction(PP) | Negative Prediction(NP) |
|
59 |
|--------------------|---------------------|---------------------|
|
60 |
| True Positive (TP) | 474 | 34 |
|