Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
patent
embeddings
mteb
text-embeddings-inference
Instructions to use datalyes/patembed-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use datalyes/patembed-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("datalyes/patembed-base") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Delete model_info.json
Browse files- model_info.json +0 -15
model_info.json
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"display_name": "patembed-base",
|
| 3 |
-
"source_folder": "train_v4/runs_distill/distill-v7-from-bert-for-patents_asym_prompt_all_1e5_bs_32_ga4_bs_nd-sp150000-proj768-prompts1_184344-3ca835/asym_prompt_all_1e5_bs_32_ga4_bs_nd-L0_2_4_6_8_10_12_14_16_18_20_22",
|
| 4 |
-
"source_path": "/media/iayaou01/Extreme SSD/patembed_artifacts/patembed_release_bundle/train_v4/runs_distill/distill-v7-from-bert-for-patents_asym_prompt_all_1e5_bs_32_ga4_bs_nd-sp150000-proj768-prompts1_184344-3ca835/asym_prompt_all_1e5_bs_32_ga4_bs_nd-L0_2_4_6_8_10_12_14_16_18_20_22",
|
| 5 |
-
"output_path": "/media/iayaou01/Extreme SSD/patembed_artifacts/patembed_release_bundle/models_for_release/patembed-base",
|
| 6 |
-
"specifications": {
|
| 7 |
-
"params": "193M",
|
| 8 |
-
"layers": 12,
|
| 9 |
-
"hidden_size": 1024,
|
| 10 |
-
"embedding_dim": 768,
|
| 11 |
-
"base_model": "Distilled from patembed-large using layers {0,2,4,6,8,10,12,14,16,18,20,22}",
|
| 12 |
-
"max_seq_length": 512,
|
| 13 |
-
"description": "Primary deployment target distilled from patembed-large. Maintains 1024 hidden size with projection to 768-dim embeddings."
|
| 14 |
-
}
|
| 15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|