Upload config.json

config.json

@@ -1,40 +1,39 @@
 {
-  "_name_or_path": "llava-v1.5-7b",
-  "architectures": ["LlavaLlamaForCausalLM"],
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "freeze_mm_mlp_adapter": false,
-  "freeze_mm_vision_resampler": false,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "image_aspect_ratio": "pad",
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_length": 4096,
-  "max_position_embeddings": 4096,
-  "mm_hidden_size": 1024,
-  "mm_projector_type": "mlp2x_gelu",
-  "mm_resampler_type": null,
-  "mm_use_im_patch_token": false,
-  "mm_use_im_start_end": false,
-  "mm_vision_select_feature": "patch",
-  "mm_vision_select_layer": -2,
-  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_token_index": 32000,
   "model_type": "llava",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-5,
-  "rope_scaling": null,
+  "pad_token_id": 32001,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "rms_norm_eps": 1e-05,
+    "torch_dtype": "float16",
+    "vocab_size": 32064
+  },
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
-  "tune_mm_mlp_adapter": false,
-  "tune_mm_vision_resampler": false,
-  "unfreeze_mm_vision_tower": false,
-  "use_cache": true,
-  "use_mm_proj": true,
-  "vocab_size": 32000
+  "transformers_version": "4.36.0.dev0",
+  "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": 32064
 }
+