Update config.json

config.json

@@ -21,7 +21,48 @@
     "mm_hidden_size": 1152,
     "mm_projector_lr": null,
     "mm_projector_type": "mlp2x_gelu",
-    "mm_vision_tower": "google/siglip-so400m-patch14-384",
+    "vision_config": {
+      "return_dict": true,
+      "tie_word_embeddings": true,
+      "max_length": 20,
+      "min_length": 0,
+      "do_sample": false,
+      "early_stopping": false,
+      "num_beams": 1,
+      "num_beam_groups": 1,
+      "diversity_penalty": 0.0,
+      "temperature": 1.0,
+      "model_type": "siglip_vision_model",
+      "hidden_size": 1152,
+      "intermediate_size": 4304,
+      "num_hidden_layers": 27,
+      "num_attention_heads": 16,
+      "num_channels": 3,
+      "patch_size": 14,
+      "image_size": 384,
+      "attention_dropout": 0.0,
+      "layer_norm_eps": 1e-06,
+      "hidden_act": "gelu_pytorch_tanh"
+    },
+    "text_config": {
+      "vocab_size": 151936,
+      "max_position_embeddings": 32768,
+      "hidden_size": 1024,
+      "intermediate_size": 2816,
+      "num_hidden_layers": 24,
+      "num_attention_heads": 16,
+      "use_sliding_window": false,
+      "sliding_window": "None",
+      "max_window_layers": 21,
+      "num_key_value_heads": 16,
+      "hidden_act": "silu",
+      "initializer_range": 0.02,
+      "rms_norm_eps": 1e-06,
+      "use_cache": false,
+      "rope_theta": 1000000.0,
+      "attention_dropout": 0.0,
+      "model_type": "qwen2"
+    },
     "model_type": "llava-qwen2",
     "num_attention_heads": 16,
     "num_hidden_layers": 24,