Upload Qwen2VLForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "saves/qwen2_vl-7b/full/sft/",
+  "_name_or_path": "saves/qwen2_vl-2b/full/sft/",
   "architectures": [
     "Qwen2VLForConditionalGeneration"
   ],
@@ -7,16 +7,16 @@
   "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 3584,
+  "hidden_size": 1536,
   "image_token_id": 151655,
   "initializer_range": 0.02,
-  "intermediate_size": 18944,
+  "intermediate_size": 8960,
   "max_position_embeddings": 32768,
   "max_window_layers": 28,
   "model_type": "qwen2_vl",
-  "num_attention_heads": 28,
+  "num_attention_heads": 12,
   "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
+  "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "mrope_section": [
@@ -29,13 +29,14 @@
   },
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
-  "tie_word_embeddings": false,
+  "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.1",
   "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,
   "vision_config": {
+    "hidden_size": 1536,
     "in_chans": 3,
     "model_type": "qwen2_vl",
     "spatial_patch_size": 14
@@ -43,5 +44,5 @@
   "vision_end_token_id": 151653,
   "vision_start_token_id": 151652,
   "vision_token_id": 151654,
-  "vocab_size": 152064
+  "vocab_size": 151936
 }

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380803bd52a4c69863eb91f611f24e955798cc968bdf3d129e32e214f4b04abb
+size 1995539928

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feeaa28c11f1f66b58e7afb592dc1c7dfac9010e4fd599c5f1ff2a2928f1d07f
+size 1993062424

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3646d8c6190db8132e8c86cd31b83811b5d3040e3e1dd3762361bb29e38b442
+size 429448016