(Trained with Unsloth)

config.json

@@ -1,32 +1,32 @@
 {
-    "architectures": [
-        "Qwen3ForCausalLM"
-    ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "eos_token_id": 151643,
-    "head_dim": 128,
-    "hidden_act": "silu",
-    "hidden_size": 2560,
-    "initializer_range": 0.02,
-    "intermediate_size": 9728,
-    "max_position_embeddings": 32768,
-    "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": "float16",
-    "transformers_version": "4.51.3",
-    "unsloth_fixed": true,
-    "unsloth_version": "2025.6.1",
-    "use_cache": true,
-    "use_sliding_window": false,
-    "vocab_size": 151936
-}
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 32768,
+  "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": "float16",
+  "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.6.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -1,8 +1,7 @@
 {
-  "bos_token_id": 151643,
+  "_from_model_config": true,
   "eos_token_id": 151643,
   "max_length": 32768,
-  "max_new_tokens": 2048,
-  "pad_token_id": 151654,
+  "pad_token_id": 0,
   "transformers_version": "4.51.3"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:132c0fb88b2070b782a69e8833d01ab987b1198ec606df151512d91820abb758
+size 11422822

tokenizer_config.json

@@ -227,7 +227,7 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|im_start|>user\n' + message['content'] + '<|im_end|>\n' }}{% elif message['role'] == 'system' %}\n{{ '<|im_start|>system\n' + message['im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% elif message['role'] == 'assistant' %}\n{{ '<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|im_start|>assistant\n' }}{% endif %}\n{% endfor %}",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + eos_token }}{% set loop_messages = messages[1:] %}{% else %}{{ 'You are given a problem.\nThink about the problem and provide your working out.\nPlace it between <start_working_out> and <end_working_out>.\nThen, provide your solution between <SOLUTION></SOLUTION>' + eos_token }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ message['content'] }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_working_out>' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "errors": "replace",