Sentence Similarity
sentence-transformers
Safetensors
t5
feature-extraction
Generated from Trainer
dataset_size:3560
loss:MultipleNegativesRankingLoss
loss:CosineSimilarityLoss
custom_code
Eval Results (legacy)
Instructions to use Bharatdeep-H/pq_cache_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Bharatdeep-H/pq_cache_2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Bharatdeep-H/pq_cache_2", trust_remote_code=True) sentences = [ "show my best performing investments over the past 5 years", "show my holdings that have performed well over the past 5 years", "Show me the geographic distribution of my investments\n", "Can you break down my exposure to X?" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download sentence_bert_config.json from Bharatdeep-H/pq_cache_2: direct link, hf CLI and curl.
- Browser
- Download file 53 Bytes
-
https://huggingface.co/Bharatdeep-H/pq_cache_2/resolve/main/sentence_bert_config.json
- Command line
-
hf download hf://Bharatdeep-H/pq_cache_2/sentence_bert_config.json
-
curl -L -o sentence_bert_config.json https://huggingface.co/Bharatdeep-H/pq_cache_2/resolve/main/sentence_bert_config.json
53 Bytes
| { | |
| "max_seq_length": 512, | |
| "do_lower_case": false | |
| } |