Spaces:
Running
on
Zero
Your space doesn't work
Your space doesn't work you have the following error on it:
Spaces
Hugging Face's logo
tiiuae
/
Falcon3-1.58bit-playground
like
6
App
Files
Community
runtime error
Exit code: 1. Reason: █████████| 826/826 [00:00<00:00, 8.17MB/s]
config.json: 0%| | 0.00/909 [00:00<?, ?B/s][A
config.json: 100%|██████████| 909/909 [00:00<00:00, 7.17MB/s]
/usr/local/lib/python3.10/site-packages/torch/cuda/init.py:716: UserWarning: Can't initialize NVML
warnings.warn("Can't initialize NVML")
You don't have a GPU available to load the model, the inference will be slow because of weight unpacking
model.safetensors: 0%| | 0.00/3.27G [00:00<?, ?B/s][A
model.safetensors: 9%|▊ | 283M/3.27G [00:01<00:10, 279MB/s][A
model.safetensors: 54%|█████▍ | 1.77G/3.27G [00:02<00:01, 987MB/s][A
model.safetensors: 100%|█████████▉| 3.27G/3.27G [00:03<00:00, 1.09GB/s][A
model.safetensors: 100%|█████████▉| 3.27G/3.27G [00:03<00:00, 980MB/s]
generation_config.json: 0%| | 0.00/118 [00:00<?, ?B/s][A
generation_config.json: 100%|██████████| 118/118 [00:00<00:00, 1.03MB/s]
Traceback (most recent call last):
File "/home/user/app/app.py", line 35, in
).to(device)
File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3698, in to
return super().to(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1340, in to
return self._apply(convert)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 900, in _apply
module._apply(fn)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 900, in _apply
module._apply(fn)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 927, in _apply
param_applied = fn(param)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1326, in convert
return t.to(
File "/usr/local/lib/python3.10/site-packages/torch/cuda/init.py", line 319, in _lazy_init
torch._C._cuda_init()
RuntimeError: No CUDA GPUs are available
Container logs:
===== Application Startup at 2025-04-17 12:26:40 =====
tokenizer_config.json: 0%| | 0.00/365k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 365k/365k [00:00<00:00, 6.80MB/s]
tokenizer.json: 0%| | 0.00/9.78M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 9.78M/9.78M [00:00<00:00, 33.0MB/s]
special_tokens_map.json: 0%| | 0.00/826 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 826/826 [00:00<00:00, 8.17MB/s]
config.json: 0%| | 0.00/909 [00:00<?, ?B/s]
config.json: 100%|██████████| 909/909 [00:00<00:00, 7.17MB/s]
/usr/local/lib/python3.10/site-packages/torch/cuda/init.py:716: UserWarning: Can't initialize NVML
warnings.warn("Can't initialize NVML")
You don't have a GPU available to load the model, the inference will be slow because of weight unpacking
model.safetensors: 0%| | 0.00/3.27G [00:00<?, ?B/s]
model.safetensors: 9%|▊ | 283M/3.27G [00:01<00:10, 279MB/s]
model.safetensors: 54%|█████▍ | 1.77G/3.27G [00:02<00:01, 987MB/s]
model.safetensors: 100%|█████████▉| 3.27G/3.27G [00:03<00:00, 1.09GB/s]
model.safetensors: 100%|█████████▉| 3.27G/3.27G [00:03<00:00, 980MB/s]
generation_config.json: 0%| | 0.00/118 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 118/118 [00:00<00:00, 1.03MB/s]
Traceback (most recent call last):
File "/home/user/app/app.py", line 35, in
).to(device)
File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3698, in to
return super().to(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1340, in to
return self._apply(convert)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 900, in _apply
module._apply(fn)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 900, in _apply
module._apply(fn)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 927, in _apply
param_applied = fn(param)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1326, in convert
return t.to(
File "/usr/local/lib/python3.10/site-packages/torch/cuda/init.py", line 319, in _lazy_init
torch._C._cuda_init()
RuntimeError: No CUDA GPUs are available
tokenizer_config.json: 0%| | 0.00/365k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 365k/365k [00:00<00:00, 12.3MB/s]
tokenizer.json: 0%| | 0.00/9.78M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 9.78M/9.78M [00:00<00:00, 33.6MB/s]
special_tokens_map.json: 0%| | 0.00/826 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 826/826 [00:00<00:00, 8.15MB/s]
config.json: 0%| | 0.00/909 [00:00<?, ?B/s]
config.json: 100%|██████████| 909/909 [00:00<00:00, 6.27MB/s]
/usr/local/lib/python3.10/site-packages/torch/cuda/init.py:716: UserWarning: Can't initialize NVML
warnings.warn("Can't initialize NVML")
You don't have a GPU available to load the model, the inference will be slow because of weight unpacking
model.safetensors: 0%| | 0.00/3.27G [00:00<?, ?B/s]
model.safetensors: 12%|█▏ | 398M/3.27G [00:01<00:07, 398MB/s]
model.safetensors: 51%|█████ | 1.66G/3.27G [00:02<00:01, 904MB/s]
model.safetensors: 100%|█████████▉| 3.27G/3.27G [00:03<00:00, 1.14GB/s]
model.safetensors: 100%|█████████▉| 3.27G/3.27G [00:03<00:00, 1.01GB/s]
generation_config.json: 0%| | 0.00/118 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 118/118 [00:00<00:00, 1.08MB/s]
Traceback (most recent call last):
File "/home/user/app/app.py", line 35, in
).to(device)
File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3698, in to
return super().to(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1340, in to
return self._apply(convert)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 900, in _apply
module._apply(fn)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 900, in _apply
module._apply(fn)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 927, in _apply
param_applied = fn(param)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1326, in convert
return t.to(
File "/usr/local/lib/python3.10/site-packages/torch/cuda/init.py", line 319, in _lazy_init
torch._C._cuda_init()
RuntimeError: No CUDA GPUs are available
/usr/local/lib/python3.10/site-packages/torch/cuda/init.py:716: UserWarning: Can't initialize NVML
warnings.warn("Can't initialize NVML")
thanks for pointing this out, it should be now fixed. Can you try again?