(Trained with Unsloth)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|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

@@ -0,0 +1,7 @@
+{% 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 %}

config.json

@@ -0,0 +1,212 @@
+{
+    "architectures": [
+        "Qwen2VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "dtype": "float16",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "image_token_id": 151655,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2_vl",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151654,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "mrope_section": [
+            16,
+            24,
+            24
+        ],
+        "rope_type": "default",
+        "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "text_config": {
+        "_name_or_path": "unsloth/Qwen2-VL-2B-Instruct",
+        "architectures": [
+            "Qwen2VLForConditionalGeneration"
+        ],
+        "attention_dropout": 0.0,
+        "dtype": "float16",
+        "eos_token_id": 151645,
+        "hidden_act": "silu",
+        "hidden_size": 1536,
+        "image_token_id": null,
+        "initializer_range": 0.02,
+        "intermediate_size": 8960,
+        "layer_types": [
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention",
+            "full_attention"
+        ],
+        "max_position_embeddings": 32768,
+        "max_window_layers": 28,
+        "model_type": "qwen2_vl_text",
+        "num_attention_heads": 12,
+        "num_hidden_layers": 28,
+        "num_key_value_heads": 2,
+        "pad_token_id": 151654,
+        "quantization_config": {
+            "_load_in_4bit": true,
+            "_load_in_8bit": false,
+            "bnb_4bit_compute_dtype": "bfloat16",
+            "bnb_4bit_quant_storage": "uint8",
+            "bnb_4bit_quant_type": "nf4",
+            "bnb_4bit_use_double_quant": true,
+            "llm_int8_enable_fp32_cpu_offload": false,
+            "llm_int8_has_fp16_weight": false,
+            "llm_int8_skip_modules": [
+                "lm_head",
+                "multi_modal_projector",
+                "merger",
+                "modality_projection",
+                "model.layers.1.mlp",
+                "visual.blocks.29.mlp",
+                "visual.blocks.21.mlp",
+                "visual.blocks.24.attn",
+                "visual.blocks.26.mlp",
+                "visual.blocks.23.attn",
+                "visual.blocks.18.mlp",
+                "visual.blocks.19.mlp",
+                "visual.blocks.22.attn",
+                "visual.blocks.17.mlp",
+                "visual.blocks.25.attn",
+                "visual.blocks.24.mlp",
+                "visual.blocks.26.attn",
+                "visual.blocks.29.attn",
+                "visual.blocks.21.attn",
+                "visual.blocks.22.mlp",
+                "visual.blocks.14.mlp",
+                "visual.blocks.23.mlp",
+                "visual.blocks.14.attn",
+                "visual.merger.mlp",
+                "visual.blocks.16.mlp",
+                "visual.blocks.20.mlp",
+                "visual.blocks.25.mlp",
+                "visual.blocks.13.mlp",
+                "visual.blocks.18.attn",
+                "visual.blocks.20.attn",
+                "visual.blocks.17.attn",
+                "visual.blocks.15.mlp",
+                "visual.blocks.27.attn",
+                "visual.blocks.28.attn",
+                "visual.blocks.12.mlp",
+                "visual.blocks.16.attn",
+                "visual.blocks.19.attn",
+                "visual.blocks.15.attn",
+                "visual.blocks.11.attn",
+                "visual.blocks.13.attn",
+                "visual.blocks.12.attn",
+                "visual.blocks.10.mlp",
+                "visual.blocks.11.mlp",
+                "visual.blocks.10.attn",
+                "visual.blocks.9.mlp",
+                "visual.blocks.5.attn",
+                "visual.blocks.9.attn",
+                "visual.blocks.4.attn",
+                "visual.blocks.6.mlp",
+                "visual.blocks.7.mlp",
+                "visual.blocks.1.attn",
+                "visual.blocks.6.attn",
+                "visual.blocks.7.attn",
+                "visual.blocks.5.mlp",
+                "visual.blocks.8.attn",
+                "visual.blocks.8.mlp",
+                "visual.blocks.4.mlp",
+                "visual.blocks.3.attn",
+                "visual.blocks.3.mlp",
+                "visual.blocks.1.mlp",
+                "visual.blocks.2.mlp",
+                "visual.blocks.2.attn",
+                "visual.blocks.0.attn",
+                "visual.blocks.0.mlp",
+                "visual.blocks.31.mlp"
+            ],
+            "llm_int8_threshold": 6.0,
+            "load_in_4bit": true,
+            "load_in_8bit": false,
+            "quant_method": "bitsandbytes"
+        },
+        "rms_norm_eps": 1e-06,
+        "rope_scaling": {
+            "mrope_section": [
+                16,
+                24,
+                24
+            ],
+            "rope_type": "default",
+            "type": "default"
+        },
+        "rope_theta": 1000000.0,
+        "sliding_window": null,
+        "tie_word_embeddings": true,
+        "unsloth_fixed": true,
+        "use_cache": true,
+        "use_sliding_window": false,
+        "video_token_id": null,
+        "vision_end_token_id": 151653,
+        "vision_start_token_id": 151652,
+        "vision_token_id": 151654,
+        "vocab_size": 151936
+    },
+    "transformers_version": "4.56.2",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.9.11",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": 151656,
+    "vision_config": {
+        "depth": 32,
+        "dtype": "float16",
+        "embed_dim": 1280,
+        "hidden_act": "quick_gelu",
+        "hidden_size": 1536,
+        "in_channels": 3,
+        "in_chans": 3,
+        "initializer_range": 0.02,
+        "mlp_ratio": 4,
+        "model_type": "qwen2_vl",
+        "num_heads": 16,
+        "patch_size": 14,
+        "spatial_merge_size": 2,
+        "spatial_patch_size": 14,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+}

preprocessor_config.json

@@ -0,0 +1,37 @@
+{
+  "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_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "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": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}