Fix config.json: correct text_config from chatterbox-ONNX reference (hidden_size=1024, num_layers=30, vocab_size=8194)

config.json

@@ -1,28 +1,47 @@
 {
   "model_type": "chatterbox",
-  "architectures": ["ChatterboxModel"],
   "text_config": {
-    "vocab_size": 131072,
-    "hidden_size": 2048,
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "intermediate_size": 5632,
-    "model_type": "llama",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
     "bos_token_id": 1,
-    "eos_token_id": 2
+    "eos_token_id": 2,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 30,
+    "num_key_value_heads": 16,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 8.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 8194
   },
   "sample_rate": 24000,
   "bos_token_id": 1,
   "eos_token_id": [2, 6562],
   "transformers.js_config": {
-    "use_external_data_format": {
-      "embed_tokens": 1,
-      "speech_encoder": 1,
-      "language_model": 1,
-      "language_model_fp16": 1,
-      "language_model_q4": 1,
-      "language_model_q4f16": 1,
-      "conditional_decoder": 1
+    "use_external_data_format": true,
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
     }
   }
 }