(Trained with Unsloth)

config.json

@@ -1,32 +1,32 @@
 {
-  "architectures": [
-    "Qwen3ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "eos_token_id": 151645,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 2560,
-  "initializer_range": 0.02,
-  "intermediate_size": 9728,
-  "max_position_embeddings": 40960,
-  "max_window_layers": 36,
-  "model_type": "qwen3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 36,
-  "num_key_value_heads": 8,
-  "pad_token_id": 151654,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
-  "sliding_window": null,
-  "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
-  "unsloth_fixed": true,
-  "unsloth_version": "2025.5.9",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
-}
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 40960,
+    "max_window_layers": 36,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151654,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.3",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.6.1",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

tokenizer_config.json

@@ -234,7 +234,7 @@
   "extra_special_tokens": {},
   "model_max_length": 40960,
   "pad_token": "<|vision_pad|>",
-  "padding_side": "left",
+  "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null