Upload Qwen3ForSequenceClassification

config.json

@@ -4,17 +4,15 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "dtype": "bfloat16",
-  "eos_token_id": 151645,
+  "dtype": "float32",
   "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 16,
+  "hidden_size": 8,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 9728,
+  "intermediate_size": 32,
   "label2id": {
     "LABEL_0": 0
   },
@@ -22,19 +20,19 @@
     "full_attention",
     "full_attention"
   ],
-  "max_position_embeddings": 40960,
-  "max_window_layers": 36,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
   "model_type": "qwen3",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 1000000,
+  "rope_theta": 10000.0,
   "sliding_window": null,
-  "tie_word_embeddings": true,
+  "tie_word_embeddings": false,
   "transformers_version": "4.57.0.dev0",
   "use_cache": true,
   "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 151669
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec6bb0a9a9262a6d4c94831822bdd35fe764e15474cc3478d136f3d1a2e3029
-size 6831912
+oid sha256:50d12fcc7f50cfd327532643e3877c9a6ea13d142ebfe5780f04c454e4d271a1
+size 4962680