Use v1.5 model in examples (#49)
Browse files- Use v1.5 model in examples (0760fbacbf3d000f3ddf79d9899336380aa00778)
Co-authored-by: Cebtenzzre <[email protected]>
README.md
CHANGED
|
@@ -2630,7 +2630,7 @@ This prefix is used for embedding texts as documents, for example as documents f
|
|
| 2630 |
```python
|
| 2631 |
from sentence_transformers import SentenceTransformer
|
| 2632 |
|
| 2633 |
-
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
|
| 2634 |
sentences = ['search_document: TSNE is a dimensionality reduction algorithm created by Laurens van Der Maaten']
|
| 2635 |
embeddings = model.encode(sentences)
|
| 2636 |
print(embeddings)
|
|
@@ -2645,7 +2645,7 @@ This prefix is used for embedding texts as questions that documents from a datas
|
|
| 2645 |
```python
|
| 2646 |
from sentence_transformers import SentenceTransformer
|
| 2647 |
|
| 2648 |
-
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
|
| 2649 |
sentences = ['search_query: Who is Laurens van Der Maaten?']
|
| 2650 |
embeddings = model.encode(sentences)
|
| 2651 |
print(embeddings)
|
|
@@ -2660,7 +2660,7 @@ This prefix is used for embedding texts in order to group them into clusters, di
|
|
| 2660 |
```python
|
| 2661 |
from sentence_transformers import SentenceTransformer
|
| 2662 |
|
| 2663 |
-
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
|
| 2664 |
sentences = ['clustering: the quick brown fox']
|
| 2665 |
embeddings = model.encode(sentences)
|
| 2666 |
print(embeddings)
|
|
@@ -2675,7 +2675,7 @@ This prefix is used for embedding texts into vectors that will be used as featur
|
|
| 2675 |
```python
|
| 2676 |
from sentence_transformers import SentenceTransformer
|
| 2677 |
|
| 2678 |
-
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
|
| 2679 |
sentences = ['classification: the quick brown fox']
|
| 2680 |
embeddings = model.encode(sentences)
|
| 2681 |
print(embeddings)
|
|
@@ -2737,8 +2737,8 @@ The model natively supports scaling of the sequence length past 2048 tokens. To
|
|
| 2737 |
+ tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192)
|
| 2738 |
|
| 2739 |
|
| 2740 |
-
- model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True)
|
| 2741 |
-
+ model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2)
|
| 2742 |
```
|
| 2743 |
|
| 2744 |
### Transformers.js
|
|
|
|
| 2630 |
```python
|
| 2631 |
from sentence_transformers import SentenceTransformer
|
| 2632 |
|
| 2633 |
+
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True)
|
| 2634 |
sentences = ['search_document: TSNE is a dimensionality reduction algorithm created by Laurens van Der Maaten']
|
| 2635 |
embeddings = model.encode(sentences)
|
| 2636 |
print(embeddings)
|
|
|
|
| 2645 |
```python
|
| 2646 |
from sentence_transformers import SentenceTransformer
|
| 2647 |
|
| 2648 |
+
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True)
|
| 2649 |
sentences = ['search_query: Who is Laurens van Der Maaten?']
|
| 2650 |
embeddings = model.encode(sentences)
|
| 2651 |
print(embeddings)
|
|
|
|
| 2660 |
```python
|
| 2661 |
from sentence_transformers import SentenceTransformer
|
| 2662 |
|
| 2663 |
+
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True)
|
| 2664 |
sentences = ['clustering: the quick brown fox']
|
| 2665 |
embeddings = model.encode(sentences)
|
| 2666 |
print(embeddings)
|
|
|
|
| 2675 |
```python
|
| 2676 |
from sentence_transformers import SentenceTransformer
|
| 2677 |
|
| 2678 |
+
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True)
|
| 2679 |
sentences = ['classification: the quick brown fox']
|
| 2680 |
embeddings = model.encode(sentences)
|
| 2681 |
print(embeddings)
|
|
|
|
| 2737 |
+ tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192)
|
| 2738 |
|
| 2739 |
|
| 2740 |
+
- model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1.5', trust_remote_code=True)
|
| 2741 |
+
+ model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1.5', trust_remote_code=True, rotary_scaling_factor=2)
|
| 2742 |
```
|
| 2743 |
|
| 2744 |
### Transformers.js
|