update

Signed-off-by: Inho Oh <[email protected]>

config.json

@@ -1,32 +1,28 @@
 {
-  "_name_or_path": "unsloth/qwen2.5-0.5b-unsloth-bnb-4bit",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "eos_token_id": 151643,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 896,
   "initializer_range": 0.02,
   "intermediate_size": 4864,
   "max_position_embeddings": 32768,
-  "max_window_layers": 24,
+  "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 14,
   "num_hidden_layers": 24,
   "num_key_value_heads": 2,
-  "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "sliding_window": 32768,
   "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
-  "unsloth_fixed": true,
-  "unsloth_version": "2025.3.17",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.1",
   "use_cache": true,
-  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,8 +1,14 @@
 {
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_length": 32768,
-  "max_new_tokens": 2048,
-  "pad_token_id": 151654,
-  "transformers_version": "4.49.0"
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.50.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa3f9a177534ef98cd35ef0463b5f346ff14ea3155be0f44a7940f12b845cd7d
-size 988097824
+oid sha256:4460d8171bf8e1a71b44a5d39130093654ac8ffb8bb03956aa286b6f3842ced6
+size 1976163472

special_tokens_map.json

@@ -14,18 +14,6 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|vision_pad|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:540b7fbf60b80e8293593a86960df91d2263723d69107ffc1afc89a7c08cda12
+size 11422162

tokenizer_config.json

@@ -195,13 +195,13 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
-  "pad_token": "<|vision_pad|>",
-  "padding_side": "left",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null