Upload DistilBertForTokenClassification

config.json

@@ -1,29 +1,24 @@
 {
-  "_name_or_path": "Qwen/Qwen2-0.5B",
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "Qwen2ForTokenClassification"
+    "DistilBertForTokenClassification"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "hidden_act": "silu",
-  "hidden_size": 896,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 4864,
-  "max_position_embeddings": 131072,
-  "max_window_layers": 24,
-  "model_type": "qwen2",
-  "num_attention_heads": 14,
-  "num_hidden_layers": 24,
-  "num_key_value_heads": 2,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": true,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.0",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f48d26693dae26a1c9dc28cbb17f07621185bf0289b2bdcc7ceaac98ff2e05
-size 1976170816
+oid sha256:6c07dfb3ba5e6f7fb9a5d589c8c77dfb38b9ba0999ca906ebd38a4a0f1f6d0a3
+size 265470008