Upload MusicgenMelodyForConditionalGeneration (#14)

- Upload MusicgenMelodyForConditionalGeneration (6eb8539b8f58210b68673406f403bb0e63ba730e)


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 sha256:803d16553a24106a5de3cefe5876f31647b6d28ae1107e8e61a71f38957040d5
-size 4978745456
+oid sha256:3deb583fd977128b24f59c86d6706f01b35b4ab8553e8355cca6969a9b7440b4
+size 4966269512

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b35f065d8992304194601dbf3cfd32621194aa0fd111b84acd4fff9efe9105
-size 1150108320
+oid sha256:01268b3a5f9819026a9ee6b76df35574e7dd521de3e6431c7fad16b44ce5a9c0
+size 1263380400

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 6128765208
+    "total_size": 6229559576
   },
   "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",
@@ -428,10 +442,10 @@
     "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",
@@ -442,12 +456,12 @@
     "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",
     "decoder.model.decoder.layers.38.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "decoder.model.decoder.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.38.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.38.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "decoder.model.decoder.layers.38.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.model.decoder.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "decoder.model.decoder.layers.38.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "decoder.model.decoder.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "decoder.model.decoder.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "decoder.model.decoder.layers.38.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "decoder.model.decoder.layers.38.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.39.fc1.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.39.fc2.weight": "model-00002-of-00002.safetensors",
     "decoder.model.decoder.layers.39.final_layer_norm.bias": "model-00002-of-00002.safetensors",