metadata
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- mteb
model-index:
- name: Jaume/gemma-2b-embeddings
results:
- dataset:
config: en
name: MTEB AmazonCounterfactualClassification (en)
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
split: test
type: mteb/amazon_counterfactual
metrics:
- type: accuracy
value: 67.49253731343282
- type: ap
value: 30.934850114823686
- type: ap_weighted
value: 30.934850114823686
- type: f1
value: 61.84797708567085
- type: f1_weighted
value: 70.73274750522187
- type: main_score
value: 67.49253731343282
task:
type: Classification
- dataset:
config: en
name: MTEB AmazonReviewsClassification (en)
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
split: test
type: mteb/amazon_reviews_multi
metrics:
- type: accuracy
value: 34.896
- type: f1
value: 34.750819111826075
- type: f1_weighted
value: 34.750819111826075
- type: main_score
value: 34.896
task:
type: Classification
- dataset:
config: default
name: MTEB Banking77Classification (default)
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
split: test
type: mteb/banking77
metrics:
- type: accuracy
value: 58.425324675324674
- type: f1
value: 58.31484701136234
- type: f1_weighted
value: 58.314847011362325
- type: main_score
value: 58.425324675324674
task:
type: Classification
- dataset:
config: default
name: MTEB EmotionClassification (default)
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
split: test
type: mteb/emotion
metrics:
- type: accuracy
value: 29.685
- type: f1
value: 26.48682675929922
- type: f1_weighted
value: 32.280528326082006
- type: main_score
value: 29.685
task:
type: Classification
widget: []
SentenceTransformer
This is a sentence-transformers model trained. It maps sentences & paragraphs to a 2048-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
Model Details
Model Description
- Model Type: Sentence Transformer
- Maximum Sequence Length: 8192 tokens
- Output Dimensionality: 2048 tokens
- Similarity Function: Cosine Similarity
Model Sources
- Documentation: Sentence Transformers Documentation
- Repository: Sentence Transformers on GitHub
- Hugging Face: Sentence Transformers on Hugging Face
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: GemmaModel
(1): Pooling({'word_embedding_dimension': 2048, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
Usage
Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("Jaume/gemma-2b-embeddings")
# Run inference
sentences = [
'The weather is lovely today.',
"It's so sunny outside!",
'He drove to the stadium.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 2048]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
Training Details
Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.3.0+cu121
- Accelerate: 0.31.0
- Datasets: 2.20.0
- Tokenizers: 0.19.1