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": 32,
     "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-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a983b7787526417b280dee6d70d28fbc825dd661b0dd50c4ae4391602d2c1f7
-size 4986994392
+oid sha256:9eda9af3032ccd59e8d198260e1bb75b3b5155ef23940f710aa3ca2648112132
+size 4987010880

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7f57ef40b093d1f69851ecde50f57eb89904aa2abd02912868447b73b212b8
-size 4966890568
+oid sha256:1df2e518045a95c6ced5aaad33d34eea40346d7e158539595134dbff3b47e469
+size 4966907208

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5aace972db765f0d5c9c7ba88119b1c1e7aae9fed43d226522f596af65c1ccf
-size 543379288
+oid sha256:a0621f095b1fb03d926437ce35af9510f50438b7d15b237aae25c7d632f6c362
+size 677597536

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 10497173784
+    "total_size": 10631424280
   },
   "weight_map": {
     "audio_enc_to_dec_proj.bias": "model-00003-of-00003.safetensors",
@@ -125,11 +125,19 @@
     "decoder.lm_heads.1.weight": "model-00003-of-00003.safetensors",
     "decoder.lm_heads.2.weight": "model-00003-of-00003.safetensors",
     "decoder.lm_heads.3.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.4.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.5.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.6.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.7.weight": "model-00003-of-00003.safetensors",
     "decoder.model.decoder.embed_positions.weights": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.embed_tokens.0.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.embed_tokens.1.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.embed_tokens.2.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.embed_tokens.3.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.4.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.5.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.6.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.7.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
     "decoder.model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
     "decoder.model.decoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
@@ -263,9 +271,9 @@
     "decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.layers.20.fc1.weight": "model-00001-of-00003.safetensors",
-    "decoder.model.decoder.layers.20.fc2.weight": "model-00001-of-00003.safetensors",
-    "decoder.model.decoder.layers.20.final_layer_norm.bias": "model-00001-of-00003.safetensors",
-    "decoder.model.decoder.layers.20.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
@@ -532,7 +540,7 @@
     "decoder.model.decoder.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.44.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.44.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.45.fc1.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.45.fc1.weight": "model-00003-of-00003.safetensors",
     "decoder.model.decoder.layers.45.fc2.weight": "model-00003-of-00003.safetensors",
     "decoder.model.decoder.layers.45.final_layer_norm.bias": "model-00003-of-00003.safetensors",
     "decoder.model.decoder.layers.45.final_layer_norm.weight": "model-00003-of-00003.safetensors",