qwen2_5vl-32b_dia_img2txt_5e-5_val_08-05

.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

Modelfile

@@ -0,0 +1,16 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+<|im_start|>assistant
+{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
+{{ end }}{{ end }}"""
+
+SYSTEM """You are a helpful assistant."""
+
+PARAMETER stop "<|im_end|>"
+PARAMETER num_ctx 4096

chat_template.json

@@ -0,0 +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 %}"
+}

config.json

@@ -30,7 +30,7 @@
   "sliding_window": 32768,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.50.0",
   "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "attn_implementation": "flash_attention_2",
   "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
@@ -9,5 +8,5 @@
   "pad_token_id": 151643,
   "repetition_penalty": 1.05,
   "temperature": 1e-06,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.50.0"
 }

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e54c6a84c67421877bcf7355f5103ab0085c45164c118cd5ce3b8568ee80c11f
+oid sha256:1198ad79ba8ac1092e8fe032032efa9f3366ca738d84bc68adb63b0cfdf0f0cb
 size 4958700928

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ec07ba590169268754b12ffccee21c508d588a49c060280ba063d2c77b19ce
+oid sha256:e186324f5a129524036932900ea69b596c546300354a87a197f4cf4f3ab6999d
 size 4928488272

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb6e6b9cf23743474c33397a0a32d20a611c7193fa237bc5383481bc59c3b2c
+oid sha256:2958c7b2e49deacde936a5c89ec6f334ceb23ac5fe8dfca28313978719937bd4
 size 4876059368

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a5b2e82eb22af1ad98825257ff086a911c263793859d27b3a21067722075f5e
+oid sha256:3da1fec7a9efbb3e94a7b4c546988d545608e3d22d696e3c74143fe16bc12e90
 size 4876059416

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:557fb051d44d2b766e73155545486e3cc08e202e1eb5031949ed4c03ff057b08
+oid sha256:5e3f68df335f910af5eafda5ad158050aa4842fec6f828ff99ef639feb0bf40e
 size 4876059416

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b350503c0104e1744fd48bbe2ecf64d2e8c97853a2a07de8a66bbaae9795582
+oid sha256:fa8642c6d492b9a64ba0d80833f6f6ae7bbd529617c9bccc9c5df831d4d98665
 size 4876059416

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb4d58d38e806b4c48c3e460ed28292e862fa3a2131b3357eaa8e02a0ef8395
+oid sha256:3a1c9701dd60b001f01b547cd2e266b2ef9f9b78026a991c6436a07a25e8b55d
 size 4876059416

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df3a3c6052097202cc6111bc79add1aa7c468846494e1d9a0d87c407271bbc82
+oid sha256:b95a5924a5c060ea617a4e0dac4f3caefdc637e0527905fe85d14ff7d60fb529
 size 4876059416

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5fb7646eb467ee494bf2a816653c21e9e86dc8bd44b7a35135a7564e62c696
+oid sha256:73354b4a6dfd2513d31cbf4469a8b148e8e9d532a346b2424e437708c7e86bb7
 size 4876059416

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c846c6dc574dab25a3d1880902799f19a0c6068aaeff9e065b26bdca0683c4
+oid sha256:8fdcde17ac2ca6905bba1b336ebe03d3471fec64781a7382112a7fd8c40368e1
 size 4876059416

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd73c1c01bd0dbc0d01ae11fa0bc33e7ee5aaceb3136cc7134f72bbfcb0a688
+oid sha256:7a464ecb1edb24e7e11b379a80660b60a8fddf695d5f6230ee26132d3a3195c3
 size 4876059416

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a27d3e09aa742c9905e0c46511ca826953d15b7079feb2ed72af5acf21e58e3
+oid sha256:452b5d917e0a675f91ec74ad3ae679cc9491f2384489ead6d0f793032e1797b6
 size 4876059416

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2cc92027aa80ab621c50d379b58fb6a962c90789de7acb139e47b8b26041125
+oid sha256:d43504574aa1ee663deaa203100d228c293c2f9deae9064ce2579d3b27a06be4
 size 4876059416

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2405d642f4f319aa3f203bab2a01304bb5acff99d5d6edbfd357f56a3473579
+oid sha256:ade6d18a1fed72e4e4ef236b8f85c49dc92ed3f16dd2b7885cba37c07c6cb6a8
 size 3381725320

preprocessor_config.json

@@ -1,4 +1,9 @@
 {
+  "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_rescale": true,
@@ -8,22 +13,24 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_processor_type": "Qwen2VLImageProcessorFast",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
-  "max_pixels": 262144,
+  "input_data_format": null,
+  "max_pixels": 12845056,
   "merge_size": 2,
-  "min_pixels": 50176,
+  "min_pixels": 3136,
   "patch_size": 14,
   "processor_class": "Qwen2_5_VLProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
   "size": {
-    "longest_edge": 262144,
-    "shortest_edge": 50176
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
   },
   "temporal_patch_size": 2
 }

training_args.bin → tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1394e696e6456ab30253404800d5f8774820f2fffb234a1c4334eaf48649964
-size 7697
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -200,9 +200,10 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 8192,
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
-  "padding_side": "right",
+  "padding_side": "left",
+  "processor_class": "Qwen2_5_VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null