Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,3 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
library_name: sentence-transformers
|
| 4 |
tags:
|
|
@@ -6,18 +5,25 @@ tags:
|
|
| 6 |
- sentence-similarity
|
| 7 |
- feature-extraction
|
| 8 |
- autotrain
|
| 9 |
-
base_model:
|
|
|
|
|
|
|
| 10 |
widget:
|
| 11 |
- source_sentence: 'search_query: i love autotrain'
|
| 12 |
sentences:
|
| 13 |
-
-
|
| 14 |
-
-
|
| 15 |
-
-
|
| 16 |
pipeline_tag: sentence-similarity
|
| 17 |
datasets:
|
| 18 |
- cnmoro/AllTripletsMsMarco-PTBR
|
|
|
|
|
|
|
|
|
|
| 19 |
---
|
| 20 |
|
|
|
|
|
|
|
| 21 |
# Model Trained Using AutoTrain
|
| 22 |
|
| 23 |
- Problem type: Sentence Transformers
|
|
@@ -27,14 +33,6 @@ loss: 0.3181200921535492
|
|
| 27 |
|
| 28 |
cosine_accuracy: 0.8921948650328134
|
| 29 |
|
| 30 |
-
runtime: 2141.8089
|
| 31 |
-
|
| 32 |
-
samples_per_second: 246.442
|
| 33 |
-
|
| 34 |
-
steps_per_second: 12.322
|
| 35 |
-
|
| 36 |
-
: 1.0
|
| 37 |
-
|
| 38 |
## Usage
|
| 39 |
|
| 40 |
### Direct Usage (Sentence Transformers)
|
|
@@ -50,12 +48,12 @@ Then you can load this model and run inference.
|
|
| 50 |
from sentence_transformers import SentenceTransformer
|
| 51 |
|
| 52 |
# Download from the Hugging Face Hub
|
| 53 |
-
model = SentenceTransformer("
|
| 54 |
# Run inference
|
| 55 |
sentences = [
|
| 56 |
-
'
|
| 57 |
-
'
|
| 58 |
-
'
|
| 59 |
]
|
| 60 |
embeddings = model.encode(sentences)
|
| 61 |
print(embeddings.shape)
|
|
@@ -63,4 +61,4 @@ print(embeddings.shape)
|
|
| 63 |
# Get the similarity scores for the embeddings
|
| 64 |
similarities = model.similarity(embeddings, embeddings)
|
| 65 |
print(similarities.shape)
|
| 66 |
-
```
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
library_name: sentence-transformers
|
| 3 |
tags:
|
|
|
|
| 5 |
- sentence-similarity
|
| 6 |
- feature-extraction
|
| 7 |
- autotrain
|
| 8 |
+
base_model:
|
| 9 |
+
- cnmoro/micro-bertim
|
| 10 |
+
- adalbertojunior/distilbert-portuguese-cased
|
| 11 |
widget:
|
| 12 |
- source_sentence: 'search_query: i love autotrain'
|
| 13 |
sentences:
|
| 14 |
+
- O pôr do sol pinta o céu com tons de laranja e vermelho
|
| 15 |
+
- Joana adora estudar matemática nas tardes de sábado
|
| 16 |
+
- Os pássaros voam em formação, criando um espetáculo no horizonte
|
| 17 |
pipeline_tag: sentence-similarity
|
| 18 |
datasets:
|
| 19 |
- cnmoro/AllTripletsMsMarco-PTBR
|
| 20 |
+
license: apache-2.0
|
| 21 |
+
language:
|
| 22 |
+
- pt
|
| 23 |
---
|
| 24 |
|
| 25 |
+
A manually pruned version of [distilbert-portuguese-cased](https://huggingface.co/adalbertojunior/distilbert-portuguese-cased), finetuned to produce high quality embeddings in a lightweight form factor.
|
| 26 |
+
|
| 27 |
# Model Trained Using AutoTrain
|
| 28 |
|
| 29 |
- Problem type: Sentence Transformers
|
|
|
|
| 33 |
|
| 34 |
cosine_accuracy: 0.8921948650328134
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
## Usage
|
| 37 |
|
| 38 |
### Direct Usage (Sentence Transformers)
|
|
|
|
| 48 |
from sentence_transformers import SentenceTransformer
|
| 49 |
|
| 50 |
# Download from the Hugging Face Hub
|
| 51 |
+
model = SentenceTransformer("cnmoro/micro-bertim-embeddings")
|
| 52 |
# Run inference
|
| 53 |
sentences = [
|
| 54 |
+
'O pôr do sol pinta o céu com tons de laranja e vermelho',
|
| 55 |
+
'Joana adora estudar matemática nas tardes de sábado',
|
| 56 |
+
'Os pássaros voam em formação, criando um espetáculo no horizonte',
|
| 57 |
]
|
| 58 |
embeddings = model.encode(sentences)
|
| 59 |
print(embeddings.shape)
|
|
|
|
| 61 |
# Get the similarity scores for the embeddings
|
| 62 |
similarities = model.similarity(embeddings, embeddings)
|
| 63 |
print(similarities.shape)
|
| 64 |
+
```
|