Upload folder using huggingface_hub

config.json

@@ -15,14 +15,14 @@
       50257
     ],
     "bos_token_id": 50257,
-    "d_model": 64,
-    "decoder_attention_heads": 2,
-    "decoder_ffn_dim": 128,
-    "decoder_layers": 1,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layers": 24,
     "decoder_start_token_id": 50258,
-    "encoder_attention_heads": 2,
-    "encoder_ffn_dim": 128,
-    "encoder_layers": 1,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layers": 24,
     "eos_token_id": 50257,
     "forced_decoder_ids": [
       [
@@ -40,7 +40,7 @@
     ],
     "max_length": 448,
     "model_type": "whisper",
-    "num_hidden_layers": 1,
+    "num_hidden_layers": 24,
     "pad_token_id": 50257,
     "suppress_tokens": [
       1,
@@ -148,8 +148,8 @@
   "hidden_act": "silu",
   "hidden_size": 256,
   "image_size": 448,
-  "init_audio": true,
-  "init_tts": true,
+  "init_audio": false,
+  "init_tts": false,
   "init_vision": true,
   "initializer_range": 0.02,
   "intermediate_size": 512,
@@ -176,15 +176,8 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.2",
   "tts_config": {
-    "hidden_size": 8,
-    "intermediate_size": 4,
-    "llm_dim": 4,
-    "model_type": "conditional_chattts",
-    "num_attention_heads": 1,
-    "num_audio_tokens": 10,
-    "num_hidden_layers": 1,
-    "num_mel_bins": 10,
-    "num_text_tokens": 20
+    "llm_dim": 3584,
+    "model_type": "conditional_chattts"
   },
   "use_cache": true,
   "use_image_id": true,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7955f2e2d47a7db417469976a67281e11a004cc9fc86b21de5ae626a1f2d11a8
-size 34895535
+oid sha256:c91ebd65c3f39ed36a031a9eb5722a54facafece3b60bcc554b6e02d624cadc4
+size 3760638