Upload DistilBertForSequenceClassification

config.json

@@ -1,37 +1,33 @@
 {
-  "activation_function": "gelu_new",
+  "activation": "gelu",
   "architectures": [
-    "GPT2ForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
   "dtype": "float32",
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
-  "n_inner": null,
-  "n_layer": 24,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "conversational": {
-      "max_length": 1000
-    }
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
   },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "transformers_version": "4.56.0",
-  "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0a927fdf7122252c081337a11987ae4d46be57eb8bc01c5d81567d5c9b41f1b
-size 1419331144
+oid sha256:61afb985df6fbe77fd84138129481f0a4444c02893782984e330f874f43cee4b
+size 267832560