Upload MusicgenMelodyForConditionalGeneration (#4)

- Upload MusicgenMelodyForConditionalGeneration (526f163f091e4fa22174da6fb353fa1f4f101a02)


Co-authored-by: Yoach Lacombe <ylacombe@users.noreply.huggingface.co>

config.json

@@ -292,5 +292,5 @@
     "vocab_size": 32128
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.38.0.dev0"
+  "transformers_version": "4.40.0.dev0"
 }

generation_config.json

@@ -6,5 +6,5 @@
   "guidance_scale": 3.0,
   "max_length": 1500,
   "pad_token_id": 2048,
-  "transformers_version": "4.38.0.dev0"
+  "transformers_version": "4.40.0.dev0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8e6a2b76bb1d9dd0c9df782893f90f00dd4d8a7c173d6b09db2e703b54e78f
-size 4991340360
+oid sha256:64bb17eb17182b17ba19dec21d794229c955d39cb5610a21da75ed2397da750d
+size 4997739040

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7afbf452e4d085b946f1721ed8af0b337fc0d782a4d78c2c4e3457d76652e7c
-size 1238202200
+oid sha256:95932e81bf5b2b02777a245a42dc65b9ab13362460ae77f7a1c3c0b50737e3c6
+size 1332599632

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 6229453080
+    "total_size": 6330247448
   },
   "weight_map": {
     "audio_enc_to_dec_proj.bias": "model-00002-of-00002.safetensors",
@@ -8,7 +8,14 @@
     "audio_encoder.decoder.layers.0.conv.bias": "model-00001-of-00002.safetensors",
     "audio_encoder.decoder.layers.0.conv.weight_g": "model-00001-of-00002.safetensors",
     "audio_encoder.decoder.layers.0.conv.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.bias_hh_l0": "model-00001-of-00002.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.bias_hh_l1": "model-00001-of-00002.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.bias_ih_l0": "model-00001-of-00002.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.bias_ih_l1": "model-00001-of-00002.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.weight_hh_l0": "model-00001-of-00002.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.weight_hh_l1": "model-00001-of-00002.safetensors",
     "audio_encoder.decoder.layers.1.lstm.weight_ih_l0": "model-00001-of-00002.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.weight_ih_l1": "model-00001-of-00002.safetensors",
     "audio_encoder.decoder.layers.10.block.1.conv.bias": "model-00001-of-00002.safetensors",
     "audio_encoder.decoder.layers.10.block.1.conv.weight_g": "model-00001-of-00002.safetensors",
     "audio_encoder.decoder.layers.10.block.1.conv.weight_v": "model-00001-of-00002.safetensors",
@@ -66,7 +73,14 @@
     "audio_encoder.encoder.layers.12.conv.bias": "model-00001-of-00002.safetensors",
     "audio_encoder.encoder.layers.12.conv.weight_g": "model-00001-of-00002.safetensors",
     "audio_encoder.encoder.layers.12.conv.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.bias_hh_l0": "model-00001-of-00002.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.bias_hh_l1": "model-00001-of-00002.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.bias_ih_l0": "model-00001-of-00002.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.bias_ih_l1": "model-00001-of-00002.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.weight_hh_l0": "model-00001-of-00002.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.weight_hh_l1": "model-00001-of-00002.safetensors",
     "audio_encoder.encoder.layers.13.lstm.weight_ih_l0": "model-00001-of-00002.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.weight_ih_l1": "model-00001-of-00002.safetensors",
     "audio_encoder.encoder.layers.15.conv.bias": "model-00001-of-00002.safetensors",
     "audio_encoder.encoder.layers.15.conv.weight_g": "model-00001-of-00002.safetensors",
     "audio_encoder.encoder.layers.15.conv.weight_v": "model-00001-of-00002.safetensors",
@@ -436,16 +450,16 @@
     "decoder.model.decoder.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "decoder.model.decoder.layers.36.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
     "decoder.model.decoder.layers.36.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.37.fc1.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.37.fc2.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.37.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.37.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.model.decoder.layers.37.fc1.weight": "model-00002-of-00002.safetensors",
+    "decoder.model.decoder.layers.37.fc2.weight": "model-00002-of-00002.safetensors",
+    "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",