AdrianBZG
/

tinyroberta-squad-es

Question Answering

Model card Files Files and versions

AdrianBZG commited on Dec 5, 2023

Commit

638082d

·

1 Parent(s): 150819b

Upload RobertaForQuestionAnswering

Files changed (2) hide show

config.json +4 -4
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "stevemobs/roberta-large-fine-tuned-squad-es",
   "architectures": [
     "RobertaForQuestionAnswering"
   ],
@@ -10,14 +10,14 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
   "num_attention_heads": 16,
-  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float16",

 {
+  "_name_or_path": "models/tinyroberta-squad-es-distilled",
   "architectures": [
     "RobertaForQuestionAnswering"
   ],
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
   "num_attention_heads": 16,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float16",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afad204ce39d673943443e3a27c5df352c262f562d19f176b324d508cf1135d3
-size 708665988

 version https://git-lfs.github.com/spec/v1
+oid sha256:6a8a29a1dbfcfeb4e811f09206a6d87ccc3c71ce4f39297960e658756a7c10a3
+size 102435660