(Trained with Unsloth)

config.json

@@ -2,13 +2,17 @@
     "architectures": [
         "Qwen3_5ForConditionalGeneration"
     ],
+    "torch_dtype": "bfloat16",
     "image_token_id": 248056,
+    "model_name": "unsloth/Qwen3.5-2B",
     "model_type": "qwen3_5",
     "mtp_num_hidden_layers": 1,
+    "pad_token_id": 248055,
     "text_config": {
         "attention_bias": false,
         "attention_dropout": 0.0,
         "attn_output_gate": true,
+        "bos_token_id": null,
         "torch_dtype": "bfloat16",
         "eos_token_id": 248044,
         "full_attention_interval": 4,
@@ -48,6 +52,7 @@
         "linear_num_key_heads": 16,
         "linear_num_value_heads": 16,
         "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
         "max_position_embeddings": 262144,
         "mlp_only_layers": [],
         "model_type": "qwen3_5_text",
@@ -56,11 +61,9 @@
         "num_attention_heads": 8,
         "num_hidden_layers": 24,
         "num_key_value_heads": 2,
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
         "rms_norm_eps": 1e-06,
-        "tie_word_embeddings": true,
-        "use_cache": true,
-        "vocab_size": 248320,
-        "mamba_ssm_dtype": "float32",
         "rope_parameters": {
             "mrope_interleaved": true,
             "mrope_section": [
@@ -68,18 +71,22 @@
                 11,
                 10
             ],
-            "rope_type": "default",
+            "partial_rotary_factor": 0.25,
             "rope_theta": 10000000,
-            "partial_rotary_factor": 0.25
-        }
+            "rope_type": "default"
+        },
+        "tie_word_embeddings": true,
+        "use_cache": true,
+        "vocab_size": 248320
     },
     "tie_word_embeddings": true,
-    "transformers_version": "4.57.0.dev0",
     "unsloth_fixed_mtp": true,
+    "unsloth_version": "2026.5.9",
     "video_token_id": 248057,
     "vision_config": {
         "deepstack_visual_indexes": [],
         "depth": 24,
+        "torch_dtype": "bfloat16",
         "hidden_act": "gelu_pytorch_tanh",
         "hidden_size": 1024,
         "in_channels": 3,

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248044,
+  "pad_token_id": 248055,
+  "transformers_version": "5.3.0",
+  "use_cache": true
+}

processor_config.json

@@ -1,31 +1,40 @@
 {
   "image_processor": {
+    "data_format": "channels_first",
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,
+    "do_resize": true,
     "image_mean": [
       0.5,
       0.5,
       0.5
     ],
-    "image_processor_type": "Qwen3VLImageProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast",
     "image_std": [
       0.5,
       0.5,
       0.5
     ],
-    "max_pixels": 16777216,
     "merge_size": 2,
-    "min_pixels": 65536,
     "patch_size": 16,
+    "resample": 3,
     "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
     "temporal_patch_size": 2
   },
   "processor_class": "Qwen3VLProcessor",
   "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
     "fps": 2,
     "image_mean": [
       0.5,
@@ -38,12 +47,16 @@
       0.5
     ],
     "max_frames": 768,
-    "max_pixels": 25165824,
     "merge_size": 2,
     "min_frames": 4,
-    "min_pixels": 4096,
     "patch_size": 16,
+    "resample": 3,
     "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
     "temporal_patch_size": 2,
     "video_processor_type": "Qwen3VLVideoProcessor"
   }

tokenizer_config.json

@@ -9,7 +9,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "image_token": "<|image_pad|>",
-  "is_local": true,
+  "is_local": false,
   "model_max_length": 262144,
   "model_specific_special_tokens": {
     "audio_bos_token": "<|audio_start|>",
@@ -29,5 +29,272 @@
   "unk_token": null,
   "video_token": "<|video_pad|>",
   "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}
+  "vision_eos_token": "<|vision_end|>",
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  },
+  "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set num_sys = 0 %}\n{%- set merged_system = '' %}\n{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n    {%- set first = render_content(messages[0].content, false, true)|trim %}\n    {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}\n        {%- set second = render_content(messages[1].content, false, true)|trim %}\n        {%- set merged_system = first + '\\n' + second %}\n        {%- set num_sys = 2 %}\n    {%- else %}\n        {%- set merged_system = first %}\n        {%- set num_sys = 1 %}\n    {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if merged_system %}\n        {{- '\\n\\n' + merged_system }}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if merged_system %}\n        {{- '<|im_start|>system\\n' + merged_system + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if loop.index0 >= num_sys and message.role != \"system\" and message.role != \"developer\" %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\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                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is mapping %}\n                    {%- for args_name in tool_call.arguments %}\n                        {%- set args_value = tool_call.arguments[args_name] %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is true %}\n        {{- '<think>\\n' }}\n    {%- else %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}\n{#- Unsloth fixes - developer role, tool calling #}\n"
+}