Sentence Similarity
sentence-transformers
Safetensors
Transformers
new
feature-extraction
mteb
multilingual
text-embeddings-inference
custom_code
Eval Results (legacy)
Instructions to use Alibaba-NLP/gte-multilingual-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Alibaba-NLP/gte-multilingual-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Alibaba-NLP/gte-multilingual-base", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use Alibaba-NLP/gte-multilingual-base with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Alibaba-NLP/gte-multilingual-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
feat(transformers): Add native Transformers config
#31
by harshaljanjani - opened
- config.json +8 -8
config.json
CHANGED
|
@@ -22,22 +22,22 @@
|
|
| 22 |
"layer_norm_eps": 1e-12,
|
| 23 |
"layer_norm_type": "layer_norm",
|
| 24 |
"max_position_embeddings": 8192,
|
| 25 |
-
"model_type": "
|
| 26 |
"num_attention_heads": 12,
|
| 27 |
"num_hidden_layers": 12,
|
| 28 |
"num_labels": 1,
|
| 29 |
"pack_qkv": true,
|
| 30 |
"pad_token_id": 1,
|
| 31 |
"position_embedding_type": "rope",
|
| 32 |
-
"rope_scaling": {
|
| 33 |
-
"factor": 8.0,
|
| 34 |
-
"type": "ntk"
|
| 35 |
-
},
|
| 36 |
-
"rope_theta": 20000,
|
| 37 |
"torch_dtype": "float16",
|
| 38 |
"transformers_version": "4.39.1",
|
| 39 |
"type_vocab_size": 1,
|
| 40 |
"unpad_inputs": false,
|
| 41 |
"use_memory_efficient_attention": false,
|
| 42 |
-
"vocab_size": 250048
|
| 43 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"layer_norm_eps": 1e-12,
|
| 23 |
"layer_norm_type": "layer_norm",
|
| 24 |
"max_position_embeddings": 8192,
|
| 25 |
+
"model_type": "gte",
|
| 26 |
"num_attention_heads": 12,
|
| 27 |
"num_hidden_layers": 12,
|
| 28 |
"num_labels": 1,
|
| 29 |
"pack_qkv": true,
|
| 30 |
"pad_token_id": 1,
|
| 31 |
"position_embedding_type": "rope",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"torch_dtype": "float16",
|
| 33 |
"transformers_version": "4.39.1",
|
| 34 |
"type_vocab_size": 1,
|
| 35 |
"unpad_inputs": false,
|
| 36 |
"use_memory_efficient_attention": false,
|
| 37 |
+
"vocab_size": 250048,
|
| 38 |
+
"rope_parameters": {
|
| 39 |
+
"rope_type": "linear",
|
| 40 |
+
"factor": 1.0671404006768237,
|
| 41 |
+
"rope_theta": 160000.0
|
| 42 |
+
}
|
| 43 |
+
}
|