Sentence Similarity
sentence-transformers
PyTorch
ONNX
Safetensors
Transformers
Transformers.js
English
nomic_bert
feature-extraction
mteb
custom_code
Eval Results (legacy)
text-embeddings-inference
Instructions to use inesaltemir/MNLP_M2_document_encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use inesaltemir/MNLP_M2_document_encoder with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("inesaltemir/MNLP_M2_document_encoder", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use inesaltemir/MNLP_M2_document_encoder with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("inesaltemir/MNLP_M2_document_encoder", trust_remote_code=True) model = AutoModel.from_pretrained("inesaltemir/MNLP_M2_document_encoder", trust_remote_code=True) - Transformers.js
How to use inesaltemir/MNLP_M2_document_encoder with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'inesaltemir/MNLP_M2_document_encoder'); - Notebooks
- Google Colab
- Kaggle
Update modeling_hf_nomic_bert.py
Browse files
modeling_hf_nomic_bert.py
CHANGED
|
@@ -1055,9 +1055,9 @@ class NomicBertModel(NomicBertPreTrainedModel):
|
|
| 1055 |
def forward(
|
| 1056 |
self,
|
| 1057 |
input_ids,
|
| 1058 |
-
position_ids=None,
|
| 1059 |
-
token_type_ids=None,
|
| 1060 |
attention_mask=None,
|
|
|
|
|
|
|
| 1061 |
return_dict=None,
|
| 1062 |
):
|
| 1063 |
if token_type_ids is None:
|
|
|
|
| 1055 |
def forward(
|
| 1056 |
self,
|
| 1057 |
input_ids,
|
|
|
|
|
|
|
| 1058 |
attention_mask=None,
|
| 1059 |
+
token_type_ids=None,
|
| 1060 |
+
position_ids=None,
|
| 1061 |
return_dict=None,
|
| 1062 |
):
|
| 1063 |
if token_type_ids is None:
|