Update files to match base model keeping quant_config intact

added_tokens.json

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

@@ -1,3 +1,3 @@
 {
-  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
-}
+    "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -1,14 +1,17 @@
 {
-  "_name_or_path": "Qwen/Qwen2-VL-72B-Instruct",
   "architectures": [
     "Qwen2VLForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
   "hidden_act": "silu",
   "hidden_size": 8192,
-  "image_token_id": 151655,
   "initializer_range": 0.02,
   "intermediate_size": 29568,
   "max_position_embeddings": 32768,
@@ -17,6 +20,14 @@
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
   "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
   "quantization_config": {
     "config_groups": {
       "group_0": {
@@ -189,32 +200,25 @@
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed"
   },
-  "rms_norm_eps": 1e-06,
+  "vision_config": {
+    "depth": 32,
+    "embed_dim": 1280,
+    "mlp_ratio": 4,
+    "num_heads": 16,
+    "in_chans": 3,
+    "hidden_size": 8192,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2
+  },
   "rope_scaling": {
+    "type": "mrope",
     "mrope_section": [
       16,
       24,
       24
-    ],
-    "rope_type": "default",
-    "type": "default"
-  },
-  "rope_theta": 1000000.0,
-  "sliding_window": 32768,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.1",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "video_token_id": 151656,
-  "vision_config": {
-    "hidden_size": 8192,
-    "in_chans": 3,
-    "model_type": "qwen2_vl",
-    "spatial_patch_size": 14
+    ]
   },
-  "vision_end_token_id": 151653,
-  "vision_start_token_id": 151652,
-  "vision_token_id": 151654,
   "vocab_size": 152064
-}
+}

generation_config.json

@@ -1,13 +1,14 @@
 {
   "bos_token_id": 151643,
+  "pad_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
     151645,
     151643
   ],
-  "pad_token_id": 151643,
   "repetition_penalty": 1.05,
-  "top_k": 1,
+  "temperature": 1,
   "top_p": 0.001,
-  "transformers_version": "4.48.1"
+  "top_k": 1,
+  "transformers_version": "4.37.0"
 }

merges.txt

@@ -1,4 +1,3 @@
-#version: 0.2
 Ġ Ġ
 ĠĠ ĠĠ
 i n

preprocessor_config.json

@@ -1,29 +1,19 @@
 {
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
   "image_mean": [
     0.48145466,
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "Qwen2VLImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
-  "max_pixels": 12845056,
-  "merge_size": 2,
-  "min_pixels": 3136,
-  "patch_size": 14,
-  "processor_class": "Qwen2VLProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "max_pixels": 12845056,
-    "min_pixels": 3136
-  },
-  "temporal_patch_size": 2
-}
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2VLProcessor"
+}

special_tokens_map.json

@@ -1,31 +0,0 @@
-{
-  "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": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:268c96d8611372617e20f95ad1eedab8c90f816f1f99ce13355e41b7700f7111
-size 11420470
+oid sha256:cb63a0a23eef3d5b01063a9880a1925a65aaf4d1591d519910ee3527852950a0
+size 7029741

tokenizer_config.json

@@ -114,31 +114,15 @@
       "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|>"
-  ],
+  "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,
   "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
+  "padding_side": "left",
   "errors": "replace",
-  "extra_special_tokens": {},
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
-  "padding_side": "left",
-  "processor_class": "Qwen2VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null