Upload Qwen2VLForConditionalGeneration

config.json

@@ -20,7 +20,9 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "mrope_section": [
-      2
+      16,
+      24,
+      24
     ],
     "rope_type": "default",
     "type": "default"
@@ -28,6 +30,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "text_config": {
+    "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
     "architectures": [
       "Qwen2VLForConditionalGeneration"
     ],
@@ -37,7 +40,6 @@
     "eos_token_id": 151645,
     "hidden_act": "silu",
     "hidden_size": 16,
-    "image_token_id": null,
     "initializer_range": 0.02,
     "intermediate_size": 8960,
     "layer_types": [
@@ -53,7 +55,8 @@
     "rms_norm_eps": 1e-06,
     "rope_scaling": {
       "mrope_section": [
-        2
+        1,
+        1
       ],
       "rope_type": "default",
       "type": "default"
@@ -63,13 +66,10 @@
     "tie_word_embeddings": 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": "4.57.0.dev0",
+  "transformers_version": "4.57.3",
   "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
-  "transformers_version": "4.57.0.dev0"
+  "transformers_version": "4.57.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a567a11def166ceec370004a74dd968cb4bc30f1077576540fda9cd7fefe7d5
+oid sha256:d3d0694f19540a10b6af744d71b28739289edcaa3b49215039b4313b6a379ef5
 size 7081872