Upload README.md
Browse files
README.md
CHANGED
@@ -1066,13 +1066,22 @@ Yinka embedding 模型是在开原模型[stella-v3.5-mrl](https://huggingface.co
|
|
1066 |
from sentence_transformers import SentenceTransformer
|
1067 |
from sklearn.preprocessing import normalize
|
1068 |
|
1069 |
-
model = SentenceTransformer("")
|
1070 |
# 注意先不要normalize! 选取前n维后再normalize
|
1071 |
vectors = model.encode(["text1", "text2"], normalize_embeddings=False)
|
1072 |
print(vectors.shape) # shape is [2,1792]
|
1073 |
n_dims = 768
|
1074 |
cut_vecs = normalize(vectors[:, :n_dims])
|
1075 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1076 |
|
1077 |
## 训练细节
|
1078 |
TODO
|
|
|
1066 |
from sentence_transformers import SentenceTransformer
|
1067 |
from sklearn.preprocessing import normalize
|
1068 |
|
1069 |
+
model = SentenceTransformer("Classical/Yinka")
|
1070 |
# 注意先不要normalize! 选取前n维后再normalize
|
1071 |
vectors = model.encode(["text1", "text2"], normalize_embeddings=False)
|
1072 |
print(vectors.shape) # shape is [2,1792]
|
1073 |
n_dims = 768
|
1074 |
cut_vecs = normalize(vectors[:, :n_dims])
|
1075 |
```
|
1076 |
+
## 结果
|
1077 |
+
| Model Name | Model Size (GB) | Dimension | Sequence Length | Classification (9) | Clustering (4) | Pair Classification (2) | Reranking (4) | Retrieval (8) | STS (8) | Average (35) |
|
1078 |
+
|:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|
1079 |
+
| [Yinka](https://huggingface.co/Classical/Yinka) | 1.21 | 1792 | 512 | 74.30 | 61.99 | 89.87 | 69.77 | 74.40 | 63.30 | 70.79 |
|
1080 |
+
| [stella-v3.5-mrl](https://huggingface.co/infgrad/stella-mrl-large-zh-v3.5-1792d) |1.21 | 1792 | 512 | 71.56 | 54.39 | 88.09 | 68.45 | 73.51 | 62.48 | 68.56 |
|
1081 |
+
| [Yinka](https://huggingface.co/Classical/Yinka) | 1.21 | 1792 | 512 | 74.30 | 61.99 | 89.87 | 69.77 | 74.40 | 63.30 | 70.79 |
|
1082 |
+
| [piccolo-large-zh-v2](https://huggingface.co/sensenova/piccolo-large-zh-v2) | 1.21 | 1792 | 512 | 74.59 | 62.17 | 90.24 | 70 | 74.36 | 63.5 | 70.95 |
|
1083 |
+
|
1084 |
+
|
1085 |
|
1086 |
## 训练细节
|
1087 |
TODO
|