Upload MusicgenMelodyForConditionalGeneration

config.json

@@ -105,7 +105,7 @@
     "add_cross_attention": false,
     "architectures": null,
     "attention_dropout": 0.0,
-    "audio_channels": 1,
+    "audio_channels": 2,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
     "bos_token_id": 2048,
@@ -145,7 +145,7 @@
     "num_attention_heads": 24,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_codebooks": 4,
+    "num_codebooks": 8,
     "num_hidden_layers": 48,
     "num_return_sequences": 1,
     "output_attentions": false,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d60f540d8a15ae3c50f63f5d4f646c0dd4bfac6442c22e481117554d0465062
-size 4966269528
+oid sha256:e20ca49644e26560e90ccf54557852c59c13e8863337bd1562fd906ef0400515
+size 4997739056

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01268b3a5f9819026a9ee6b76df35574e7dd521de3e6431c7fad16b44ce5a9c0
-size 1263380400
+oid sha256:95932e81bf5b2b02777a245a42dc65b9ab13362460ae77f7a1c3c0b50737e3c6
+size 1332599632

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 6229559576
+    "total_size": 6330247448
   },
   "weight_map": {
     "audio_enc_to_dec_proj.bias": "model-00002-of-00002.safetensors",
@@ -125,11 +125,19 @@
     "decoder.lm_heads.1.weight": "model-00002-of-00002.safetensors",
     "decoder.lm_heads.2.weight": "model-00002-of-00002.safetensors",
     "decoder.lm_heads.3.weight": "model-00002-of-00002.safetensors",
+    "decoder.lm_heads.4.weight": "model-00002-of-00002.safetensors",
+    "decoder.lm_heads.5.weight": "model-00002-of-00002.safetensors",
+    "decoder.lm_heads.6.weight": "model-00002-of-00002.safetensors",
+    "decoder.lm_heads.7.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.embed_positions.weights": "model-00001-of-00002.safetensors",
     "decoder.model.decoder.embed_tokens.0.weight": "model-00001-of-00002.safetensors",
     "decoder.model.decoder.embed_tokens.1.weight": "model-00001-of-00002.safetensors",
     "decoder.model.decoder.embed_tokens.2.weight": "model-00001-of-00002.safetensors",
     "decoder.model.decoder.embed_tokens.3.weight": "model-00001-of-00002.safetensors",
+    "decoder.model.decoder.embed_tokens.4.weight": "model-00001-of-00002.safetensors",
+    "decoder.model.decoder.embed_tokens.5.weight": "model-00001-of-00002.safetensors",
+    "decoder.model.decoder.embed_tokens.6.weight": "model-00001-of-00002.safetensors",
+    "decoder.model.decoder.embed_tokens.7.weight": "model-00001-of-00002.safetensors",
     "decoder.model.decoder.layer_norm.bias": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layer_norm.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
@@ -447,11 +455,11 @@
     "decoder.model.decoder.layers.37.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.37.final_layer_norm.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.37.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "decoder.model.decoder.layers.37.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "decoder.model.decoder.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.37.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.37.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.model.decoder.layers.37.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "decoder.model.decoder.layers.37.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.38.fc1.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.38.fc2.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.38.final_layer_norm.bias": "model-00002-of-00002.safetensors",