Add files using upload-large-folder tool

config.json

@@ -4,7 +4,6 @@
     "Qwen2VLForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 1536,
@@ -32,36 +31,67 @@
       "multi_modal_projector",
       "merger",
       "modality_projection",
-      "visual.blocks.0.attn",
-      "visual.blocks.0.mlp",
-      "visual.blocks.1.attn",
-      "visual.blocks.1.mlp",
-      "visual.blocks.2.attn",
-      "visual.blocks.2.mlp",
-      "visual.blocks.3.attn",
-      "visual.blocks.3.mlp",
-      "visual.blocks.4.attn",
-      "visual.blocks.4.mlp",
+      "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.5.mlp",
-      "visual.blocks.6.attn",
+      "visual.blocks.9.attn",
+      "visual.blocks.4.attn",
       "visual.blocks.6.mlp",
-      "visual.blocks.7.attn",
       "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.9.attn",
-      "visual.blocks.9.mlp",
-      "visual.blocks.10.attn",
-      "visual.blocks.10.mlp",
-      "visual.blocks.11.attn",
-      "visual.blocks.11.mlp",
-      "visual.blocks.12.attn",
-      "visual.blocks.12.mlp",
-      "visual.blocks.15.attn",
-      "visual.blocks.16.attn",
-      "visual.blocks.25.mlp",
-      "visual.blocks.31.mlp.fc2"
+      "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,
@@ -82,7 +112,7 @@
   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.49.0",
   "unsloth_fixed": true,
   "use_cache": true,
   "use_sliding_window": false,
@@ -91,7 +121,8 @@
     "hidden_size": 1536,
     "in_chans": 3,
     "model_type": "qwen2_vl",
-    "spatial_patch_size": 14
+    "spatial_patch_size": 14,
+    "torch_dtype": "bfloat16"
   },
   "vision_end_token_id": 151653,
   "vision_start_token_id": 151652,

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 0.01,
   "top_k": 1,
   "top_p": 0.001,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.49.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1615f9d6c684d976925ca4ed4c0e935fd5e4d6e71eaf77c60e38a992afbbc92
-size 1968265232
+oid sha256:94098b958a0f6b882e12d4f1d0982d338234af9f258015538b9c33eebf9d972e
+size 2457389953

preprocessor_config.json

@@ -22,8 +22,8 @@
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "max_pixels": 12845056,
-    "min_pixels": 3136
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
   },
   "temporal_patch_size": 2
 }

tokenizer_config.json

@@ -134,6 +134,7 @@
   "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",