Sentence Similarity
sentence-transformers
ONNX
Safetensors
Chinese
English
modernbert
embeddings
medical
clinical-nlp
healthcare
biomedical
fhir
traditional-chinese
taiwan
rag
text-embeddings-inference
Instructions to use weemed/IlhaEmbed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use weemed/IlhaEmbed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("weemed/IlhaEmbed") sentences = [ "帶狀皰疹", "皮蛇", "高血壓用藥", "114年成健" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
release: update IlhaEmbed with expanded clinical lab & procedural contrastive tuning
Browse files- config.json +26 -3
config.json
CHANGED
|
@@ -16,7 +16,6 @@
|
|
| 16 |
"embedding_dropout": 0.0,
|
| 17 |
"eos_token_id": 25464,
|
| 18 |
"global_attn_every_n_layers": 3,
|
| 19 |
-
"global_rope_theta": 150000.0,
|
| 20 |
"gradient_checkpointing": false,
|
| 21 |
"hidden_activation": "silu",
|
| 22 |
"hidden_size": 384,
|
|
@@ -24,8 +23,21 @@
|
|
| 24 |
"initializer_range": 0.02,
|
| 25 |
"intermediate_size": 1536,
|
| 26 |
"layer_norm_eps": 1e-05,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"local_attention": 128,
|
| 28 |
-
"local_rope_theta": 160000.0,
|
| 29 |
"max_position_embeddings": 32768,
|
| 30 |
"mlp_bias": false,
|
| 31 |
"mlp_dropout": 0.0,
|
|
@@ -37,9 +49,20 @@
|
|
| 37 |
"pad_token_id": 25461,
|
| 38 |
"position_embedding_type": "absolute",
|
| 39 |
"repad_logits_with_grad": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
"sep_token_id": 25464,
|
| 41 |
"sparse_pred_ignore_index": -100,
|
| 42 |
"sparse_prediction": false,
|
| 43 |
-
"
|
|
|
|
| 44 |
"vocab_size": 25526
|
| 45 |
}
|
|
|
|
| 16 |
"embedding_dropout": 0.0,
|
| 17 |
"eos_token_id": 25464,
|
| 18 |
"global_attn_every_n_layers": 3,
|
|
|
|
| 19 |
"gradient_checkpointing": false,
|
| 20 |
"hidden_activation": "silu",
|
| 21 |
"hidden_size": 384,
|
|
|
|
| 23 |
"initializer_range": 0.02,
|
| 24 |
"intermediate_size": 1536,
|
| 25 |
"layer_norm_eps": 1e-05,
|
| 26 |
+
"layer_types": [
|
| 27 |
+
"full_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention"
|
| 39 |
+
],
|
| 40 |
"local_attention": 128,
|
|
|
|
| 41 |
"max_position_embeddings": 32768,
|
| 42 |
"mlp_bias": false,
|
| 43 |
"mlp_dropout": 0.0,
|
|
|
|
| 49 |
"pad_token_id": 25461,
|
| 50 |
"position_embedding_type": "absolute",
|
| 51 |
"repad_logits_with_grad": false,
|
| 52 |
+
"rope_parameters": {
|
| 53 |
+
"full_attention": {
|
| 54 |
+
"rope_theta": 150000.0,
|
| 55 |
+
"rope_type": "default"
|
| 56 |
+
},
|
| 57 |
+
"sliding_attention": {
|
| 58 |
+
"rope_theta": 160000.0,
|
| 59 |
+
"rope_type": "default"
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
"sep_token_id": 25464,
|
| 63 |
"sparse_pred_ignore_index": -100,
|
| 64 |
"sparse_prediction": false,
|
| 65 |
+
"tie_word_embeddings": true,
|
| 66 |
+
"transformers_version": "5.12.1",
|
| 67 |
"vocab_size": 25526
|
| 68 |
}
|