Upload config

config.json

@@ -11,6 +11,7 @@
   "freeze_mm_vision_resampler": false,
   "hidden_act": "silu",
   "hidden_size": 4096,
+  "ignore_index": -100,
   "image_aspect_ratio": "anyres",
   "image_crop_resolution": 224,
   "image_grid_pinpoints": [
@@ -36,6 +37,7 @@
     ]
   ],
   "image_split_resolution": 224,
+  "image_token_index": 32000,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 4096,
@@ -50,24 +52,41 @@
   "mm_vision_select_layer": -2,
   "mm_vision_tower": "openai/clip-vit-large-patch14-336",
   "mm_vision_tower_lr": 2e-06,
-  "model_type": "llava_llama",
+  "model_type": "llava",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pad_token_id": 0,
+  "pad_token_id": 32001,
   "pretraining_tp": 1,
+  "projector_hidden_act": "gelu",
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
+  "text_config": {
+    "model_type": "llama"
+  },
   "tie_word_embeddings": false,
   "tokenizer_model_max_length": 4096,
   "tokenizer_padding_side": "right",
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.37.2",
   "tune_mm_mlp_adapter": false,
   "tune_mm_vision_resampler": false,
   "unfreeze_mm_vision_tower": true,
   "use_cache": true,
   "use_mm_proj": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
   "vocab_size": 32000
 }