0
YuE: OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model
App: YuE (yue.git)
Repo: https://github.com/pinokiofactory/yue.git
Generated: 2026-09-25T00:00:26.103Z
Pinokio: 8.2.0
Platform: win32 x64
Node: v22.21.1
Summary: I am a complete code novice. This is my first foray into Pinokio and I have never done any coding, so i am feeling my way through an install and operation of YuE. It appears to be trying to open, but hits this error repeatedly. I note that those python files appear to be in a Home subdirectory, cache folder under the BIN/PY folder in Pinokio. When I open soundstream_hubert_new.py (in Notepad ++) there is no line 3765. It ends on line 214. What is going on ehre? And what can I do to get it working right?
System
{
"pinokio": {
"version": "8.2.0",
"node": "v22.21.1",
"platform": "win32",
"arch": "x64"
},
"hardware": {
"gpu": "nvidia",
"gpu_model": "nvidia t1000 8gb",
"ram_gb": 16,
"vram_gb": 8,
"gpu_driver": "596.51",
"gpu_target": "sm_75"
},
"os": {
"platform": "Windows",
"distro": "Microsoft Windows 10 Home",
"release": "10.0.19045",
"codename": "22H2",
"kernel": "10.0.19045",
"arch": "x64",
"build": "19045",
"servicepack": "0.0",
"uefi": false
},
"system": {
"manufacturer": "Dell Inc.",
"model": "Precision T5610",
"version": "00",
"virtual": false
},
"cpu": {
"manufacturer": "Intel",
"brand": "Xeon® E5-2620 v2",
"vendor": "GenuineIntel",
"family": "6",
"model": "62",
"stepping": "4",
"revision": "15876",
"speed": 2.1,
"speedMin": 2.1,
"speedMax": 2.1,
"cores": 12,
"physicalCores": 6,
"processors": 1,
"performanceCores": 12,
"efficiencyCores": 0,
"virtualization": false,
"cache": {
"l1d": 0,
"l1i": 0,
"l2": 1572864,
"l3": 15728640
}
},
"memory": {
"total": 17121382400,
"free": 8370499584,
"used": 8750882816,
"active": 8750882816,
"available": 8370499584,
"buffers": 0,
"cached": 0,
"slab": 0,
"buffcache": 0,
"swaptotal": 17179869184,
"swapused": 756023296,
"swapfree": 16423845888
},
"gpus": [
{
"model": "nvidia t1000 8gb"
}
],
"graphics": {
"controllers": [
{
"vendor": "NVIDIA",
"model": "NVIDIA T1000 8GB",
"bus": "PCI",
"vram": 8192,
"vramDynamic": false,
"driverVersion": "596.51"
}
],
"displays": [
{
"model": "ONA4HB19T01",
"main": true,
"builtin": false,
"connection": "DVI",
"currentResX": 1920,
"currentResY": 1080,
"resolutionX": 1920,
"resolutionY": 1080,
"pixelDepth": 32,
"currentRefreshRate": 60
},
{
"model": "ONA4HB19T01",
"main": false,
"builtin": false,
"connection": "DVI",
"currentResX": 1920,
"currentResY": 1080,
"resolutionX": 1920,
"resolutionY": 1080,
"pixelDepth": 32,
"currentRefreshRate": 60
}
]
},
"diagnostics": {
"platform": "win32",
"arch": "x64",
"running": {},
"home": "F:\\pinokio",
"vars": {
"pip": {
"install": {
"torch": "pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118"
}
}
},
"memory": {
"local": {},
"global": {},
"rpc": {
"F:\\pinokio\\api\\yue.git\\start.js": {
"method": "shell.run",
"params": {
"venv": "../env",
"env": {
"SERVER_PORT": 42003
},
"path": "app/inference",
"message": [
"python gradio_server.py --profile {{args.profile}} {{args.icl ? '--icl' : ''}} {{args.compile ? '--compile' : ''}}"
],
"on": [
{
"event": "/http://\\S+/",
"done": true
}
]
}
}
},
"input": {
"F:\\pinokio\\api\\yue.git\\start.js": {
"profile": "1",
"icl": "true"
}
},
"args": {
"F:\\pinokio\\api\\yue.git\\start.js": {
"profile": "1",
"icl": "true"
}
}
},
"procs": {},
"gpu": "nvidia",
"gpus": [
{
"name": "nvidia",
"model": "nvidia t1000 8gb",
"driver": "596.51"
}
],
"gpu_model": "nvidia t1000 8gb",
"gpu_driver": "596.51",
"gpu_target": "sm_75",
"ram": 16,
"vram": 8,
"version": "8.2.0",
"audio": [
{
"id": "HDAUDIO\\FUNC_01&VEN_10EC&DEV_0280&SUBSYS_102805D3&REV_1000\\4&810A44E&0&0001",
"name": "Realtek High Definition Audio",
"manufacturer": "Realtek",
"revision": null,
"driver": null,
"default": null,
"channel": null,
"type": "Sound Driver",
"in": null,
"out": null,
"status": "enabled"
},
{
"id": "HDAUDIO\\FUNC_01&VEN_10DE&DEV_0094&SUBSYS_17AA1612&REV_1001\\5&29535E51&0&0001",
"name": "NVIDIA High Definition Audio",
"manufacturer": "NVIDIA",
"revision": null,
"driver": null,
"default": null,
"channel": null,
"type": "Sound Driver",
"in": null,
"out": null,
"status": "enabled"
},
{
"id": "FOCUSRITEUSB\\AUDIO&ADAPTER\\1&2C3F869&1&",
"name": "Focusrite USB Audio",
"manufacturer": "Focusrite Audio Engineering, Ltd.",
"revision": null,
"driver": null,
"default": null,
"channel": null,
"type": "",
"in": null,
"out": null,
"status": "enabled"
},
{
"id": "ROOT\\MEDIA\\0000",
"name": "Waves SoundGrid",
"manufacturer": "Waves Audio Ltd.",
"revision": null,
"driver": null,
"default": null,
"channel": null,
"type": "",
"in": null,
"out": null,
"status": "enabled"
}
],
"mem": {
"total": 17121382400,
"free": 8370499584,
"used": 8750882816,
"active": 8750882816,
"available": 8370499584,
"buffers": 0,
"cached": 0,
"slab": 0,
"buffcache": 0,
"reclaimable": 0,
"swaptotal": 17179869184,
"swapused": 756023296,
"swapfree": 16423845888,
"writeback": null,
"dirty": null
},
"graphics": {
"controllers": [
{
"vendor": "NVIDIA",
"model": "NVIDIA T1000 8GB",
"bus": "PCI",
"vram": 8192,
"vramDynamic": false,
"subDeviceId": "0x161217AA",
"driverVersion": "596.51",
"name": "NVIDIA T1000 8GB",
"pciBus": "00000000:02:00.0",
"fanSpeed": 34,
"memoryTotal": 8192,
"memoryUsed": 559,
"memoryFree": 7457,
"utilizationGpu": 13,
"utilizationMemory": 11,
"temperatureGpu": 51,
"powerLimit": 50,
"clockCore": 300,
"clockMemory": 405
}
],
"displays": [
{
"vendor": "ONN",
"model": "ONA4HB19T01",
"serial": "16843009",
"productionYear": 2018,
"displayId": "display\\onn0101\\5&1da12e45&0&uid8453_0",
"deviceName": "\\\\.\\DISPLAY1",
"main": true,
"builtin": false,
"connection": "DVI",
"resolutionX": 1920,
"resolutionY": 1080,
"sizeX": 52,
"sizeY": 32,
"pixelDepth": 32,
"currentResX": 1920,
"currentResY": 1080,
"positionX": 0,
"positionY": 0,
"currentRefreshRate": 60
},
{
"vendor": "ONN",
"model": "ONA4HB19T01",
"serial": "16843009",
"productionYear": 2018,
"displayId": "display\\onn0101\\5&1da12e45&0&uid8455_0",
"deviceName": "\\\\.\\DISPLAY2",
"main": false,
"builtin": false,
"connection": "DVI",
"resolutionX": 1920,
"resolutionY": 1080,
"sizeX": 52,
"sizeY": 32,
"pixelDepth": 32,
"currentResX": 1920,
"currentResY": 1080,
"positionX": 1920,
"positionY": 0,
"currentRefreshRate": 60
}
]
},
"osInfo": {
"platform": "Windows",
"distro": "Microsoft Windows 10 Home",
"release": "10.0.19045",
"codename": "22H2",
"kernel": "10.0.19045",
"arch": "x64",
"hostname": "DigiStation",
"fqdn": "DIGISTATION",
"codepage": "437",
"logofile": "windows",
"serial": "00326-10000-00000-AA630",
"build": "19045",
"servicepack": "0.0",
"uefi": false,
"hypervisor": false,
"remoteSession": false
},
"cpu": {
"manufacturer": "Intel",
"brand": "Xeon® E5-2620 v2",
"vendor": "GenuineIntel",
"family": "6",
"model": "62",
"stepping": "4",
"revision": "15876",
"voltage": "",
"speed": 2.1,
"speedMin": 2.1,
"speedMax": 2.1,
"governor": "",
"cores": 12,
"physicalCores": 6,
"performanceCores": 12,
"efficiencyCores": 0,
"processors": 1,
"socket": "LGA2011",
"flags": "de pse tsc msr mce sep mtrr mca cmov psn clfsh ds acpi mmx fxsr sse sse2 ss htt tm ia64 pbe",
"virtualization": false,
"cache": {
"l1d": 0,
"l1i": 0,
"l2": 1572864,
"l3": 15728640
}
},
"shell": "CMD",
"system": {
"manufacturer": "Dell Inc.",
"model": "Precision T5610",
"version": "00",
"serial": "3BL7DZ1",
"uuid": "4c4c4544-0042-4c10-8037-b3c04f445a31",
"sku": "05D3",
"virtual": false
}
}
}
Logs
logs/api/start.js/1790294308009
Source: api / start.js
Lines: 40 total, last 40 included
[api shell.run]
Microsoft Windows [Version 10.0.19045.6466]
(c) Microsoft Corporation. All rights reserved.
F:\pinokio\api\yue.git\app\inference>conda_hook & conda deactivate & conda
deactivate & conda deactivate & conda activate base & F:\pinokio\api\yue.gi
t\app\env\Scripts\activate F:\pinokio\api\yue.git\app\env & bluefairy-activ
ate.cmd && python gradio_server.py --profile 1 --icl
[OK] bluefairy active: uv/npm/bun protection enabled
You are attempting to use Flash Attention 2.0 with a model not initialized
on GPU. Make sure to move the model to GPU after initializing it on CPU wit
h `model.to('cuda')`.
Loading checkpoint shards: 100%|████████████| 3/3 [00:00<00:00, 3.02it/s]
F:\Pinokio\api\yue.git\app\env\Lib\site-packages\torch\nn\utils\weight_norm
.py:143: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor
of `torch.nn.utils.parametrizations.weight_norm`.
WeightNorm.apply(module, name, dim)
Traceback (most recent call last):
File "F:\pinokio\api\yue.git\app\inference\gradio_server.py", line 134, i
n <module>
codec_model = eval(model_config.generator.name)(**model_config.generato
r.config).to(device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^
File "F:\pinokio\api\yue.git\app\inference\xcodec_mini_infer\models\sound
stream_hubert_new.py", line 102, in __init__
self.semantic_model = AutoModel.from_pretrained("./xcodec_mini_infer/se
mantic_ckpts/hf_1_325000")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Pinokio\api\yue.git\app\env\Lib\site-packages\transformers\model
s\auto\auto_factory.py", line 564, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Pinokio\api\yue.git\app\env\Lib\site-packages\transformers\model
ing_utils.py", line 3765, in from_pretrained
raise EnvironmentError(
OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model
.h5, model.ckpt.index or flax_model.msgpack found in directory ./xcodec_min
i_infer/semantic_ckpts/hf_1_325000.
Replies (0)
Up to 10 files, 25MB each. Images are optimized; GIFs -> MP4; videos 720p (max 120s).
