Sentence Similarity
sentence-transformers
Safetensors
qwen3
feature-extraction
dense
Generated from Trainer
dataset_size:127731
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use KayaTechAI/Qwen3-0.6B-Fine-Tuned-Telecom-Technical-Documents-Retrieval-Embedding-With-Config with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use KayaTechAI/Qwen3-0.6B-Fine-Tuned-Telecom-Technical-Documents-Retrieval-Embedding-With-Config with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("KayaTechAI/Qwen3-0.6B-Fine-Tuned-Telecom-Technical-Documents-Retrieval-Embedding-With-Config") sentences = [ "How does the Session Description Protocol (SDP) typically facilitate media session setup?", "The Serving GPRS Support Node (SGSN) typically initiates a PDP context activation procedure towards the GGSN after receiving a request from the mobile device.", "SDP is used to describe the parameters for media streams, such as codecs, transport protocols, and IP addresses, enabling endpoints to agree on how to exchange media.", "They show the order of the bits produced by the speech encoder." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "word_embedding_dimension": 1024, | |
| "pooling_mode_cls_token": false, | |
| "pooling_mode_mean_tokens": false, | |
| "pooling_mode_max_tokens": false, | |
| "pooling_mode_mean_sqrt_len_tokens": false, | |
| "pooling_mode_weightedmean_tokens": false, | |
| "pooling_mode_lasttoken": true, | |
| "include_prompt": true | |
| } |