zli12321
/

answer_equivalence_tiny_bert

Text Classification

question-answering

text-embeddings-inference

Model card Files Files and versions

zli12321 commited on Oct 31, 2024

Commit

6a8d047

·

verified ·

1 Parent(s): d219143

Updated more powerful models

Files changed (2) hide show

config.json +5 -5
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/srv/www/active-topic-modeling/ae_tune/models--google--bert_uncased_L-2_H-128_A-2/snapshots/30b0a37ccaaa32f332884b96992754e246e48c5f",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -7,14 +7,14 @@
   "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 128,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

 {
+  "_name_or_path": "/srv/www/active-topic-modeling/ae_tune/models--google--bert_uncased_L-4_H-256_A-4/snapshots/387825ce42dbb39b87911cdf8e383ee3b25184f8",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
   "initializer_range": 0.02,
+  "intermediate_size": 1024,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e737403eedecbc205d922eff07f07a3eaf4b324d697fb890cce3f1ca409eb57
-size 17549312

 version https://git-lfs.github.com/spec/v1
+oid sha256:c585ee3f29794eb0dbf01bada1ba6b3bff9a1bec1dbde62f997b74c5d942b50d
+size 44692608