Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

added_tokens.json

@@ -1,3 +1,16 @@
 {
-  "<image_soft_token>": 262144
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
 }

chat_template.jinja

@@ -1,47 +1,7 @@
-{{ bos_token }}
-{%- if messages[0]['role'] == 'system' -%}
-    {%- if messages[0]['content'] is string -%}
-        {%- set first_user_prefix = messages[0]['content'] + '
-
-' -%}
-    {%- else -%}
-        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
-
-' -%}
-    {%- endif -%}
-    {%- set loop_messages = messages[1:] -%}
-{%- else -%}
-    {%- set first_user_prefix = "" -%}
-    {%- set loop_messages = messages -%}
-{%- endif -%}
-{%- for message in loop_messages -%}
-    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
-        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
-    {%- endif -%}
-    {%- if (message['role'] == 'assistant') -%}
-        {%- set role = "model" -%}
-    {%- else -%}
-        {%- set role = message['role'] -%}
-    {%- endif -%}
-    {{ '<start_of_turn>' + role + '
-' + (first_user_prefix if loop.first else "") }}
-    {%- if message['content'] is string -%}
-        {{ message['content'] | trim }}
-    {%- elif message['content'] is iterable -%}
-        {%- for item in message['content'] -%}
-            {%- if item['type'] == 'image' -%}
-                {{ '<start_of_image>' }}
-            {%- elif item['type'] == 'text' -%}
-                {{ item['text'] | trim }}
-            {%- endif -%}
-        {%- endfor -%}
-    {%- else -%}
-        {{ raise_exception("Invalid content type") }}
-    {%- endif -%}
-    {{ '<end_of_turn>
-' }}
-{%- endfor -%}
-{%- if add_generation_prompt -%}
-    {{'<start_of_turn>model
-'}}
-{%- endif -%}
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

preprocessor_config.json

@@ -1,29 +1,37 @@
 {
-  "do_convert_rgb": null,
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
   "do_normalize": true,
-  "do_pan_and_scan": null,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.5,
-    0.5,
-    0.5
+    0.48145466,
+    0.4578275,
+    0.40821073
   ],
-  "image_processor_type": "Gemma3ImageProcessor",
-  "image_seq_length": 256,
+  "image_processor_type": "Qwen2VLImageProcessorFast",
   "image_std": [
-    0.5,
-    0.5,
-    0.5
+    0.26862954,
+    0.26130258,
+    0.27577711
   ],
-  "pan_and_scan_max_num_crops": null,
-  "pan_and_scan_min_crop_size": null,
-  "pan_and_scan_min_ratio_to_activate": null,
-  "processor_class": "Gemma3Processor",
-  "resample": 2,
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
   "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
   "size": {
-    "height": 896,
-    "width": 896
-  }
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
 }

special_tokens_map.json

@@ -1,30 +1,28 @@
 {
-  "boi_token": "<start_of_image>",
-  "bos_token": {
-    "content": "<bos>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eoi_token": "<end_of_image>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
   "eos_token": {
-    "content": "<end_of_turn>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "image_token": "<image_soft_token>",
   "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<|vision_pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7666402c0617d170e6b0a985b3130c3fb0795393aa0970600994a5d9aae12351
-size 33384822
+oid sha256:00ff1d43b119596534f778ecc067f5b457d2ce2fe2665ab12fe7a8705fda3437
+size 11420639