Update config.json

config.json

@@ -7,7 +7,7 @@
   "audio_config": {
     "_name_or_path": "",
     "add_cross_attention": false,
-    "aff_block_r": 4,
+    "aff_block_r": 2,
     "architectures": null,
     "attention_dropout": 0.1,
     "attention_probs_dropout_prob": 0.0,
@@ -20,8 +20,6 @@
     "depths": [
       2,
       2,
-      6,
-      2
     ],
     "diversity_penalty": 0.0,
     "do_sample": false,
@@ -73,7 +71,7 @@
     "num_beams": 1,
     "num_channels": 3,
     "num_classes": 527,
-    "num_hidden_layers": 4,
+    "num_hidden_layers": 3,
     "num_mel_bins": 64,
     "num_return_sequences": 1,
     "output_attentions": false,
@@ -116,8 +114,8 @@
   "initializer_factor": 1.0,
   "logit_scale_init_value": 14.285714285714285,
   "model_type": "clap",
-  "num_hidden_layers": 9,
-  "projection_dim": 64,
+  "num_hidden_layers": 3,
+  "projection_dim": 32,
   "projection_hidden_act": "relu",
   "text_config": {
     "_name_or_path": "",
@@ -165,10 +163,10 @@
     "min_length": 0,
     "model_type": "clap_text_model",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 4,
+    "num_attention_heads": 2,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 5,
+    "num_hidden_layers": 3,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
@@ -177,7 +175,7 @@
     "position_embedding_type": "absolute",
     "prefix": null,
     "problem_type": null,
-    "projection_dim": 64,
+    "projection_dim": 32,
     "projection_hidden_act": "relu",
     "pruned_heads": {},
     "remove_invalid_values": false,
@@ -201,7 +199,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 99
+    "vocab_size": 50265
   },
   "torch_dtype": "float32",
   "transformers_version": null