Upload Qwen2_5_VLForConditionalGeneration

config.json

@@ -7,15 +7,15 @@
   "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": {
@@ -69,13 +69,12 @@
     "vision_token_id": 151654,
     "vocab_size": 151936
   },
-  "transformers_version": "4.57.0.dev0",
+  "transformers_version": "4.56.1",
   "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,
   "vision_config": {
     "depth": 32,
-    "embed_dim": 64,
     "fullatt_block_indexes": [
       7,
       15,

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": "4.56.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3865269868b24a598d1d4646b2f7f2fa10cfd8115b012f0a44a341a7657a557d
+oid sha256:19b535be9b7ca8fcf573c46c58abccacb04b0999d10d9495eec88473d5584cdc
 size 18086192