Proper eos_token_id

eos_token_id for that architecture must be 151645, check out https://huggingface.co/Qwen/QwQ-32B/blob/main/config.json

config.json

@@ -1,29 +1,29 @@
-{
-  "_name_or_path": "Qwen/Qwen2.5-32B",
-  "architectures": [
-    "Qwen2ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "hidden_act": "silu",
-  "hidden_size": 5120,
-  "initializer_range": 0.02,
-  "intermediate_size": 27648,
-  "max_position_embeddings": 131072,
-  "max_window_layers": 64,
-  "model_type": "qwen2",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 64,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": 131072,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151665
-}
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}