Upload Qwen2_5_VLForConditionalGeneration

config.json

@@ -7,22 +7,21 @@
   "dtype": "bfloat16",
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 16,
   "image_token_id": 151655,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 128000,
   "max_window_layers": 70,
   "model_type": "qwen2_5_vl",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 36,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "mrope_section": [
-      16,
-      24,
-      24
+      1,
+      1
     ],
     "rope_type": "default",
     "type": "default"
@@ -30,7 +29,6 @@
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "text_config": {
-    "_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
     "architectures": [
       "Qwen2_5_VLForConditionalGeneration"
     ],
@@ -40,6 +38,7 @@
     "eos_token_id": 151645,
     "hidden_act": "silu",
     "hidden_size": 16,
+    "image_token_id": null,
     "initializer_range": 0.02,
     "intermediate_size": 11008,
     "layer_types": [
@@ -66,10 +65,13 @@
     "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": "4.57.1",
+  "transformers_version": "4.56.1",
   "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": "4.57.1"
+  "transformers_version": "4.56.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ee6de012cbabb328744133306ae85256f9d1d994145c50a0a341918c7af35c
+oid sha256:1adaecbcf061f2bbc1cc4e00dcfdd13424e9d25abb3c9d6b014f423e3b6d1bc8
 size 18086192