Update config.json

config.json

@@ -1,9 +1,8 @@
 {
   {
     "architectures": [
-      "MistralForCausalLM"
+      "MistralForCausalLM", "WhisperForConditionalGeneration"
     ],
-    "_name_or_path": "LeroyDyer/Mixtral_AI_Multi_Input_Model",
     "attention_dropout": 0.0,
     "bos_token_id": 1,
     "eos_token_id": 2,
@@ -24,12 +23,6 @@
     "transformers_version": "4.36.0",
     "use_cache": true,
     "vocab_size": 32000
-  }
-  {  
-    "_name_or_path": "LeroyDyer/Mixtral_AI_Multi_Input_Model/Sound",
-    "architectures": [
-      "WhisperForConditionalGeneration"
-    ],
     "activation_dropout": 0.0,
     "activation_function": "gelu",
     "attention_dropout": 0.0,
@@ -37,7 +30,6 @@
       220,
       50256
     ],
-    "bos_token_id": 50257,
     "d_model": 1024,
     "decoder_attention_heads": 16,
     "decoder_ffn_dim": 4096,
@@ -158,16 +150,6 @@
       50360,
       50361
     ],
-    "torch_dtype": "float32",
-    "transformers_version": "4.27.0.dev0",
-    "use_cache": true,
-    "vocab_size": 51864
-  }
-  {
-    "_name_or_path": "LeroyDyer/Mixtral_AI_Multi_Input_Model/Video",
-    "architectures": [
-      "XClipModel"
-    ],
     "initializer_factor": 1.0,
     "logit_scale_init_value": 2.6592,
     "model_type": "xclip",
@@ -246,11 +228,8 @@
       "top_p": 1.0,
       "torch_dtype": null,
       "torchscript": false,
-      "transformers_version": "4.22.0.dev0",
       "typical_p": 1.0,
       "use_bfloat16": false,
-      "vocab_size": 49408
-    },
     "text_config_dict": null,
     "torch_dtype": "float32",
     "transformers_version": null,
@@ -336,12 +315,6 @@
       "use_bfloat16": false
       "vision_config_dict": null
     }
-  }
-  {
-    "_name_or_path": "LeroyDyer/Mixtral_AI_Multi_Input_Model/Image",
-    "architectures": [
-      "CLIPModel"
-    ],
     "initializer_factor": 1.0,
     "logit_scale_init_value": 2.6592,
     "model_type": "clip",