Instructions to use dongjicheng/roformer-tiny-matcher with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dongjicheng/roformer-tiny-matcher with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="dongjicheng/roformer-tiny-matcher")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("dongjicheng/roformer-tiny-matcher") model = AutoModel.from_pretrained("dongjicheng/roformer-tiny-matcher", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
1.私域训练集百万,比ada召回率
|
| 2 |
2.速度快,上下文长度1536,向量维度 768。
|
| 3 |
|
| 4 |
|
|
@@ -6,7 +6,7 @@
|
|
| 6 |
|
| 7 |
from sentence_transformers import SentenceTransformer
|
| 8 |
|
| 9 |
-
model = SentenceTransformer('dongjicheng/
|
| 10 |
|
| 11 |
|
| 12 |
sentences = [
|
|
@@ -16,10 +16,4 @@ sentences = [
|
|
| 16 |
]
|
| 17 |
|
| 18 |
|
| 19 |
-
embeddings = model.encode(sentences)
|
| 20 |
-
|
| 21 |
-
#Print the embeddings
|
| 22 |
-
for sentence, embedding in zip(sentences, embeddings):
|
| 23 |
-
print("Sentence:", sentence)
|
| 24 |
-
print("Embedding:", embedding)
|
| 25 |
-
print("")
|
|
|
|
| 1 |
+
1.私域训练集百万,比ada召回率高30%。
|
| 2 |
2.速度快,上下文长度1536,向量维度 768。
|
| 3 |
|
| 4 |
|
|
|
|
| 6 |
|
| 7 |
from sentence_transformers import SentenceTransformer
|
| 8 |
|
| 9 |
+
model = SentenceTransformer('dongjicheng/roformer_tiny_matcher')
|
| 10 |
|
| 11 |
|
| 12 |
sentences = [
|
|
|
|
| 16 |
]
|
| 17 |
|
| 18 |
|
| 19 |
+
embeddings = model.encode(sentences)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|