|
|
--- |
|
|
base_model: Mihaiii/Bulbasaur |
|
|
license: mit |
|
|
library_name: sentence-transformers |
|
|
pipeline_tag: sentence-similarity |
|
|
tags: |
|
|
- sentence-transformers |
|
|
- feature-extraction |
|
|
- sentence-similarity |
|
|
- gte |
|
|
- mteb |
|
|
datasets: |
|
|
- Mihaiii/qa-assistant |
|
|
--- |
|
|
# Venusaur |
|
|
|
|
|
This is a distill of [Bulbasaur](https://huggingface.co/Mihaiii/Bulbasaur) using [qa-assistant](https://huggingface.co/datasets/Mihaiii/qa-assistant). |
|
|
|
|
|
## Intended purpose |
|
|
|
|
|
<span style="color:blue">This model is designed for use in semantic-autocomplete ([click here for demo](https://mihaiii.github.io/semantic-autocomplete/)).</span> |
|
|
|
|
|
## Usage (Sentence-Transformers) (same as [gte-tiny](https://huggingface.co/TaylorAI/gte-tiny)) |
|
|
|
|
|
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: |
|
|
|
|
|
``` |
|
|
pip install -U sentence-transformers |
|
|
``` |
|
|
|
|
|
Then you can use the model like this: |
|
|
|
|
|
```python |
|
|
from sentence_transformers import SentenceTransformer |
|
|
sentences = ["This is an example sentence", "Each sentence is converted"] |
|
|
|
|
|
model = SentenceTransformer('Mihaiii/Venusaur') |
|
|
embeddings = model.encode(sentences) |
|
|
print(embeddings) |
|
|
``` |
|
|
|
|
|
|
|
|
|
|
|
## Usage (HuggingFace Transformers) (same as [gte-tiny](https://huggingface.co/TaylorAI/gte-tiny)) |
|
|
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModel |
|
|
import torch |
|
|
|
|
|
|
|
|
#Mean Pooling - Take attention mask into account for correct averaging |
|
|
def mean_pooling(model_output, attention_mask): |
|
|
token_embeddings = model_output[0] #First element of model_output contains all token embeddings |
|
|
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() |
|
|
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) |
|
|
|
|
|
|
|
|
# Sentences we want sentence embeddings for |
|
|
sentences = ['This is an example sentence', 'Each sentence is converted'] |
|
|
|
|
|
# Load model from HuggingFace Hub |
|
|
tokenizer = AutoTokenizer.from_pretrained('Mihaiii/Venusaur') |
|
|
model = AutoModel.from_pretrained('Mihaiii/Venusaur') |
|
|
|
|
|
# Tokenize sentences |
|
|
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') |
|
|
|
|
|
# Compute token embeddings |
|
|
with torch.no_grad(): |
|
|
model_output = model(**encoded_input) |
|
|
|
|
|
# Perform pooling. In this case, mean pooling. |
|
|
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) |
|
|
|
|
|
print("Sentence embeddings:") |
|
|
print(sentence_embeddings) |
|
|
``` |
|
|
|
|
|
### Limitation (same as [gte-small](https://huggingface.co/thenlper/gte-small)) |
|
|
This model exclusively caters to English texts, and any lengthy texts will be truncated to a maximum of 512 tokens. |
