Upload MusicgenMelodyForConditionalGeneration (#4)

- Upload MusicgenMelodyForConditionalGeneration (26b5a7209f2d93ef7ce851d4bfc7cc28bcb7dba3)


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-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e43bd318ddca719ccbb8562eec0da47fddc2ac5a428032a528414fc1587bea4
-size 4986895072
+oid sha256:de1f894560846ddcaa2c8a2259229e135bcab586ec5002145869777ce0a15a5a
+size 4987010864

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd20fc6e8fed30387d8322c84224986918fbd6d9e051d25e062f1ab21c324cd7
-size 4933335864
+oid sha256:1df2e518045a95c6ced5aaad33d34eea40346d7e158539595134dbff3b47e469
+size 4966907208

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e25e0a8ed5d455a5b58152cbb3467a52170a2245c376995846b9f37dd1e58c
-size 610488552
+oid sha256:a0621f095b1fb03d926437ce35af9510f50438b7d15b237aae25c7d632f6c362
+size 677597536

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 10530629912
+    "total_size": 10631424280
   },
   "weight_map": {
     "audio_enc_to_dec_proj.bias": "model-00003-of-00003.safetensors",
@@ -8,7 +8,14 @@
     "audio_encoder.decoder.layers.0.conv.bias": "model-00001-of-00003.safetensors",
     "audio_encoder.decoder.layers.0.conv.weight_g": "model-00001-of-00003.safetensors",
     "audio_encoder.decoder.layers.0.conv.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.bias_hh_l0": "model-00001-of-00003.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.bias_hh_l1": "model-00001-of-00003.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.bias_ih_l0": "model-00001-of-00003.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.bias_ih_l1": "model-00001-of-00003.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.weight_hh_l0": "model-00001-of-00003.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.weight_hh_l1": "model-00001-of-00003.safetensors",
     "audio_encoder.decoder.layers.1.lstm.weight_ih_l0": "model-00001-of-00003.safetensors",
+    "audio_encoder.decoder.layers.1.lstm.weight_ih_l1": "model-00001-of-00003.safetensors",
     "audio_encoder.decoder.layers.10.block.1.conv.bias": "model-00001-of-00003.safetensors",
     "audio_encoder.decoder.layers.10.block.1.conv.weight_g": "model-00001-of-00003.safetensors",
     "audio_encoder.decoder.layers.10.block.1.conv.weight_v": "model-00001-of-00003.safetensors",
@@ -66,7 +73,14 @@
     "audio_encoder.encoder.layers.12.conv.bias": "model-00001-of-00003.safetensors",
     "audio_encoder.encoder.layers.12.conv.weight_g": "model-00001-of-00003.safetensors",
     "audio_encoder.encoder.layers.12.conv.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.bias_hh_l0": "model-00001-of-00003.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.bias_hh_l1": "model-00001-of-00003.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.bias_ih_l0": "model-00001-of-00003.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.bias_ih_l1": "model-00001-of-00003.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.weight_hh_l0": "model-00001-of-00003.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.weight_hh_l1": "model-00001-of-00003.safetensors",
     "audio_encoder.encoder.layers.13.lstm.weight_ih_l0": "model-00001-of-00003.safetensors",
+    "audio_encoder.encoder.layers.13.lstm.weight_ih_l1": "model-00001-of-00003.safetensors",
     "audio_encoder.encoder.layers.15.conv.bias": "model-00001-of-00003.safetensors",
     "audio_encoder.encoder.layers.15.conv.weight_g": "model-00001-of-00003.safetensors",
     "audio_encoder.encoder.layers.15.conv.weight_v": "model-00001-of-00003.safetensors",
@@ -257,9 +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",
@@ -270,10 +284,10 @@
     "decoder.model.decoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
@@ -526,7 +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",