Git Product home page Git Product logo

jukemir's People

Contributors

chrisdonahue avatar rodrigo-castellon avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

jukemir's Issues

AssertionError: Found no NVIDIA driver on your system

when i run the shell
docker run -it --rm -v xxx/video_trim_audio/:/input -v /xxx/jukemir/wav_jukebox/:/output 393fa1440720

I get the error

Traceback (most recent call last):
File "main.py", line 151, in
rank, local_rank, device = setup_dist_from_mpi()
File "/code/jukebox/jukebox/utils/dist_utils.py", line 46, in setup_dist_from_mpi
return _setup_dist_from_mpi(master_addr, backend, port, n_attempts, verbose)
File "/code/jukebox/jukebox/utils/dist_utils.py", line 93, in _setup_dist_from_mpi
torch.cuda.set_device(local_rank)
File "/usr/local/lib/python3.6/dist-packages/torch/cuda/init.py", line 292, in set_device
torch._C._cuda_setDevice(device)
File "/usr/local/lib/python3.6/dist-packages/torch/cuda/init.py", line 196, in _lazy_init
_check_driver()
File "/usr/local/lib/python3.6/dist-packages/torch/cuda/init.py", line 101, in _check_driver
http://www.nvidia.com/Download/index.aspx""")
AssertionError:
Found no NVIDIA driver on your system. Please check that you
have an NVIDIA GPU and installed a driver from
http://www.nvidia.com/Download/index.aspx

Dockerfile incomplete?

Hi,

I am interested in extracting jukebox representations with my own dataset. I've looked at the readme where you provide a Docker environment and instructions and how to process data. However, I am running in a server cluster where Docker containers are not well supported.

I was thinking of replicating the environment by looking at the source DockerFile, but it seems to be different than the command list in the docker image. Ideally I would like to create a conda environment or similar, and just install python related packages and avoid low level installations.

Do you know if this is possible? Are there any alternatives?

Thanks

Errors when running collab notebook

Hello,
I am experiencing a series of errors when trying to run the collab notebook provided with the code.

First, installing jukebox throws the following error:

× python setup.py bdist_wheel did not run successfully.
  │ exit code: 1
  ╰─> See above for output.

However, this can be solved by installing a different version of jukebox:

!pip install --upgrade git+https://github.com/craftmine1000/jukebox-saveopt.git

However, then in the initialization block, the following errors arise:

/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:2025: UserWarning: for encoders.0.level_blocks.0.model.0.0.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:2025: UserWarning: for encoders.0.level_blocks.0.model.0.0.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:2025: UserWarning: for encoders.0.level_blocks.0.model.0.1.model.0.model.1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
...
``` in the line: `top_prior = make_prior(hparams, vqvae, device)#device)`

Please advise on how to resolve. Thanks in advance

3_extract.sh not generating outputs

Hi, really appreciate this nice work. I stumbled upon a problem when trying to reproduce the experimental results. After executing 3_extract.sh following the instructions in README, there is nothing inside the representation output folder, say ~/.jukemir/representations/gtzan_ff/jukebox, and the terminal only generated the following texts without indicating errors.

lab812@lab812-Z390-UD:~/jukemir/reproduce$ bash 3_extract.sh 
  0%|                                                                                                                                   | 0/4 [00:00<?, ?it/s]Using cuda True
Downloading from azure
Restored from /root/.cache/jukebox/models/5b/vqvae.pth.tar
0: Loading vqvae in eval mode
lab812@lab812-Z390-UD:

Is it because the hardware does not meet your execution criteria (at least 30GB of RAM and a GPU with at least 12GB)?
Thanks for your reply in advance!

Model selection for extracting jukebox representations

Hello,

I would like to ask a question regarding the language model selection in the main script for extracting jukebox representations. I am referring to the main python script under jukemir/representations/jukebox.

There are two options for the language model, '5b' or '1b_lyrics'. However, when setting parameters there are a couple of if statements referring to a model '5b_lyrics'. Please see the below excerpt of the code from line 153 onwards:

# Set up VQVAE
model = "5b"  # or "1b_lyrics"
hps = Hyperparams()
hps.sr = 44100
hps.n_samples = 3 if model == "5b_lyrics" else 8
hps.name = "samples"
chunk_size = 16 if model == "5b_lyrics" else 32
max_batch_size = 3 if model == "5b_lyrics" else 16

Is there a choice between three different models or "5b" is identical to "5b_lyrics"? Which values did you use for n_samples, chunk_size and max_batch_size when using the pretrained 5B-parameter language model for extracting representations for the datasets you used in the paper?

Thank you!

RuntimeError: CuDNN Error: CUDNN_STATUS_MAPPING_ERROR

When I ran the docker, I first got the found no nvidia driver error as issue. After installing nvidia-container, the problem seemed solved.

Then I tried again the following command. Since I have 2 cards on the machine, only card 0 is assigned.
sudo docker run -it --rm --gpus='"device=0"' -v xxx:/input -v xxx:/output --entrypoint bash jukemir/representations_jukebox
And then,
python main.py --batch_size 8

After a few minutes (of initializing I guess), I got the following error:
Traceback (most recent call last):
File "main.py", line 177, in
representation = get_acts_from_file(input_path, hps, vqvae, top_prior, meanpool=True)
File "main.py", line 86, in get_acts_from_file
z = get_z(audio, vqvae)
File "main.py", line 27, in get_z
zs = vqvae.encode(torch.cuda.FloatTensor(audio[np.newaxis, :, np.newaxis]))
File "/code/jukebox/jukebox/vqvae/vqvae.py", line 141, in encode
zs_i = self._encode(x_i, start_level=start_level, end_level=end_level)
File "/code/jukebox/jukebox/vqvae/vqvae.py", line 132, in _encode
x_out = encoder(x_in)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/code/jukebox/jukebox/vqvae/encdec.py", line 80, in forward
x = level_block(x)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/code/jukebox/jukebox/vqvae/encdec.py", line 26, in forward
return self.model(x)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/conv.py", line 202, in forward
self.padding, self.dilation, self.groups)
RuntimeError: cuDNN error: CUDNN_STATUS_MAPPING_ERROR

I googled it and added torch.backends.cudnn.enabled = False to main.py but a new problem occurred:
Traceback (most recent call last):
File "main.py", line 179, in
representation = get_acts_from_file(input_path, hps, vqvae, top_prior, meanpool=True)
File "main.py", line 88, in get_acts_from_file
z = get_z(audio, vqvae)
File "main.py", line 29, in get_z
zs = vqvae.encode(torch.cuda.FloatTensor(audio[np.newaxis, :, np.newaxis]))
File "/code/jukebox/jukebox/vqvae/vqvae.py", line 141, in encode
zs_i = self._encode(x_i, start_level=start_level, end_level=end_level)
File "/code/jukebox/jukebox/vqvae/vqvae.py", line 132, in _encode
x_out = encoder(x_in)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/code/jukebox/jukebox/vqvae/encdec.py", line 80, in forward
x = level_block(x)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/code/jukebox/jukebox/vqvae/encdec.py", line 26, in forward
return self.model(x)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/conv.py", line 202, in forward
self.padding, self.dilation, self.groups)
RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)

Did I miss anything?

ValueError: Audio file is not long enough

restore jukebox/models/5b/prior_level_2.pth.tar
Restored from jukebox/models/5b/prior_level_2.pth.tar
0%| | 0/60 [00:35<?, ?it/s]
Traceback (most recent call last):
File "main.py", line 177, in
representation = get_acts_from_file(input_path, hps, vqvae, top_prior, meanpool=True)
File "main.py", line 86, in get_acts_from_file
z = get_z(audio, vqvae)
File "main.py", line 32, in get_z
raise ValueError('Audio file is not long enough')
ValueError: Audio file is not long enough

RuntimeError: Error(s) in loading state_dict for SimplePrior

Hello,

Thank you for making your work public.
I am having an issue when trying to extract a jukebox representation using the model "5b".
My python script is identical to your main under /representations/jukebox where I am using a different dataset.

Please see the exact error below

0: Loading vqvae in eval mode
Loading artist IDs from /data/home/acw512/musicnet_vgg_multitask/lib/python3.8/site-packages/jukebox/data/ids/v2_artist_ids.txt
Loading artist IDs from /data/home/acw512/musicnet_vgg_multitask/lib/python3.8/site-packages/jukebox/data/ids/v2_genre_ids.txt
Level:2, Cond downsample:None, Raw to tokens:128, Sample length:1048576
0: Converting to fp16 params
Downloading from azure
Running  wget -O /data/home/acw512/.cache/jukebox/models/5b/prior_level_2.pth.tar https://openaipublic.azureedge.net/jukebox/models/5b/prior_level_2.pth.tar
Restored from /data/home/acw512/.cache/jukebox/models/5b/prior_level_2.pth.tar
Traceback (most recent call last):
  File "test_representation.py", line 139, in <module>
    top_prior = make_prior(hparams, vqvae, device)
  File "/data/home/acw512/musicnet_vgg_multitask/lib/python3.8/site-packages/jukebox/make_models.py", line 179, in make_prior
    restore_model(hps, prior, hps.restore_prior)
  File "/data/home/acw512/musicnet_vgg_multitask/lib/python3.8/site-packages/jukebox/make_models.py", line 61, in restore_model
    model.load_state_dict(checkpoint['model'])
  File "/data/home/acw512/musicnet_vgg_multitask/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1406, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for SimplePrior:
	Unexpected key(s) in state_dict: "prior.transformer._attn_mods.36.attn.c_attn.w", "prior.transformer._attn_mods.36.attn.c_attn.b", "prior.transformer._attn_mods.36.attn.c_proj.w", "prior.transformer._attn_mods.36.attn.c_proj.b", "prior.transformer._attn_mods.36.ln_0.weight", "prior.transformer._attn_mods.36.ln_0.bias", "prior.transformer._attn_mods.36.mlp.c_fc.w", "prior.transformer._attn_mods.36.mlp.c_fc.b", "prior.transformer._attn_mods.36.mlp.c_proj.w", "prior.transformer._attn_mods.36.mlp.c_proj.b", "prior.transformer._attn_mods.36.ln_1.weight", "prior.transformer._attn_mods.36.ln_1.bias", "prior.transformer._attn_mods.37.attn.c_attn.w", "prior.transformer._attn_mods.37.attn.c_attn.b", "prior.transformer._attn_mods.37.attn.c_proj.w", "prior.transformer._attn_mods.37.attn.c_proj.b", "prior.transformer._attn_mods.37.ln_0.weight", "prior.transformer._attn_mods.37.ln_0.bias", "prior.transformer._attn_mods.37.mlp.c_fc.w", "prior.transformer._attn_mods.37.mlp.c_fc.b", "prior.transformer._attn_mods.37.mlp.c_proj.w", "prior.transformer._attn_mods.37.mlp.c_proj.b", "prior.transformer._attn_mods.37.ln_1.weight", "prior.transformer._attn_mods.37.ln_1.bias", "prior.transformer._attn_mods.38.attn.c_attn.w", "prior.transformer._attn_mods.38.attn.c_attn.b", "prior.transformer._attn_mods.38.attn.c_proj.w", "prior.transformer._attn_mods.38.attn.c_proj.b", "prior.transformer._attn_mods.38.ln_0.weight", "prior.transformer._attn_mods.38.ln_0.bias", "prior.transformer._attn_mods.38.mlp.c_fc.w", "prior.transformer._attn_mods.38.mlp.c_fc.b", "prior.transformer._attn_mods.38.mlp.c_proj.w", "prior.transformer._attn_mods.38.mlp.c_proj.b", "prior.transformer._attn_mods.38.ln_1.weight", "prior.transformer._attn_mods.38.ln_1.bias", "prior.transformer._attn_mods.39.attn.c_attn.w", "prior.transformer._attn_mods.39.attn.c_attn.b", "prior.transformer._attn_mods.39.attn.c_proj.w", "prior.transformer._attn_mods.39.attn.c_proj.b", "prior.transformer._attn_mods.39.ln_0.weight", "prior.transformer._attn_mods.39.ln_0.bias", "prior.transformer._attn_mods.39.mlp.c_fc.w", "prior.transformer._attn_mods.39.mlp.c_fc.b", "prior.transformer._attn_mods.39.mlp.c_proj.w", "prior.transformer._attn_mods.39.mlp.c_proj.b", "prior.transformer._attn_mods.39.ln_1.weight", "prior.transformer._attn_mods.39.ln_1.bias", "prior.transformer._attn_mods.40.attn.c_attn.w", "prior.transformer._attn_mods.40.attn.c_attn.b", "prior.transformer._attn_mods.40.attn.c_proj.w", "prior.transformer._attn_mods.40.attn.c_proj.b", "prior.transformer._attn_mods.40.ln_0.weight", "prior.transformer._attn_mods.40.ln_0.bias", "prior.transformer._attn_mods.40.mlp.c_fc.w", "prior.transformer._attn_mods.40.mlp.c_fc.b", "prior.transformer._attn_mods.40.mlp.c_proj.w", "prior.transformer._attn_mods.40.mlp.c_proj.b", "prior.transformer._attn_mods.40.ln_1.weight", "prior.transformer._attn_mods.40.ln_1.bias", "prior.transformer._attn_mods.41.attn.c_attn.w", "prior.transformer._attn_mods.41.attn.c_attn.b", "prior.transformer._attn_mods.41.attn.c_proj.w", "prior.transformer._attn_mods.41.attn.c_proj.b", "prior.transformer._attn_mods.41.ln_0.weight", "prior.transformer._attn_mods.41.ln_0.bias", "prior.transformer._attn_mods.41.mlp.c_fc.w", "prior.transformer._attn_mods.41.mlp.c_fc.b", "prior.transformer._attn_mods.41.mlp.c_proj.w", "prior.transformer._attn_mods.41.mlp.c_proj.b", "prior.transformer._attn_mods.41.ln_1.weight", "prior.transformer._attn_mods.41.ln_1.bias", "prior.transformer._attn_mods.42.attn.c_attn.w", "prior.transformer._attn_mods.42.attn.c_attn.b", "prior.transformer._attn_mods.42.attn.c_proj.w", "prior.transformer._attn_mods.42.attn.c_proj.b", "prior.transformer._attn_mods.42.ln_0.weight", "prior.transformer._attn_mods.42.ln_0.bias", "prior.transformer._attn_mods.42.mlp.c_fc.w", "prior.transformer._attn_mods.42.mlp.c_fc.b", "prior.transformer._attn_mods.42.mlp.c_proj.w", "prior.transformer._attn_mods.42.mlp.c_proj.b", "prior.transformer._attn_mods.42.ln_1.weight", "prior.transformer._attn_mods.42.ln_1.bias", "prior.transformer._attn_mods.43.attn.c_attn.w", "prior.transformer._attn_mods.43.attn.c_attn.b", "prior.transformer._attn_mods.43.attn.c_proj.w", "prior.transformer._attn_mods.43.attn.c_proj.b", "prior.transformer._attn_mods.43.ln_0.weight", "prior.transformer._attn_mods.43.ln_0.bias", "prior.transformer._attn_mods.43.mlp.c_fc.w", "prior.transformer._attn_mods.43.mlp.c_fc.b", "prior.transformer._attn_mods.43.mlp.c_proj.w", "prior.transformer._attn_mods.43.mlp.c_proj.b", "prior.transformer._attn_mods.43.ln_1.weight", "prior.transformer._attn_mods.43.ln_1.bias", "prior.transformer._attn_mods.44.attn.c_attn.w", "prior.transformer._attn_mods.44.attn.c_attn.b", "prior.transformer._attn_mods.44.attn.c_proj.w", "prior.transformer._attn_mods.44.attn.c_proj.b", "prior.transformer._attn_mods.44.ln_0.weight", "prior.transformer._attn_mods.44.ln_0.bias", "prior.transformer._attn_mods.44.mlp.c_fc.w", "prior.transformer._attn_mods.44.mlp.c_fc.b", "prior.transformer._attn_mods.44.mlp.c_proj.w", "prior.transformer._attn_mods.44.mlp.c_proj.b", "prior.transformer._attn_mods.44.ln_1.weight", "prior.transformer._attn_mods.44.ln_1.bias", "prior.transformer._attn_mods.45.attn.c_attn.w", "prior.transformer._attn_mods.45.attn.c_attn.b", "prior.transformer._attn_mods.45.attn.c_proj.w", "prior.transformer._attn_mods.45.attn.c_proj.b", "prior.transformer._attn_mods.45.ln_0.weight", "prior.transformer._attn_mods.45.ln_0.bias", "prior.transformer._attn_mods.45.mlp.c_fc.w", "prior.transformer._attn_mods.45.mlp.c_fc.b", "prior.transformer._attn_mods.45.mlp.c_proj.w", "prior.transformer._attn_mods.45.mlp.c_proj.b", "prior.transformer._attn_mods.45.ln_1.weight", "prior.transformer._attn_mods.45.ln_1.bias", "prior.transformer._attn_mods.46.attn.c_attn.w", "prior.transformer._attn_mods.46.attn.c_attn.b", "prior.transformer._attn_mods.46.attn.c_proj.w", "prior.transformer._attn_mods.46.attn.c_proj.b", "prior.transformer._attn_mods.46.ln_0.weight", "prior.transformer._attn_mods.46.ln_0.bias", "prior.transformer._attn_mods.46.mlp.c_fc.w", "prior.transformer._attn_mods.46.mlp.c_fc.b", "prior.transformer._attn_mods.46.mlp.c_proj.w", "prior.transformer._attn_mods.46.mlp.c_proj.b", "prior.transformer._attn_mods.46.ln_1.weight", "prior.transformer._attn_mods.46.ln_1.bias", "prior.transformer._attn_mods.47.attn.c_attn.w", "prior.transformer._attn_mods.47.attn.c_attn.b", "prior.transformer._attn_mods.47.attn.c_proj.w", "prior.transformer._attn_mods.47.attn.c_proj.b", "prior.transformer._attn_mods.47.ln_0.weight", "prior.transformer._attn_mods.47.ln_0.bias", "prior.transformer._attn_mods.47.mlp.c_fc.w", "prior.transformer._attn_mods.47.mlp.c_fc.b", "prior.transformer._attn_mods.47.mlp.c_proj.w", "prior.transformer._attn_mods.47.mlp.c_proj.b", "prior.transformer._attn_mods.47.ln_1.weight", "prior.transformer._attn_mods.47.ln_1.bias", "prior.transformer._attn_mods.48.attn.c_attn.w", "prior.transformer._attn_mods.48.attn.c_attn.b", "prior.transformer._attn_mods.48.attn.c_proj.w", "prior.transformer._attn_mods.48.attn.c_proj.b", "prior.transformer._attn_mods.48.ln_0.weight", "prior.transformer._attn_mods.48.ln_0.bias", "prior.transformer._attn_mods.48.mlp.c_fc.w", "prior.transformer._attn_mods.48.mlp.c_fc.b", "prior.transformer._attn_mods.48.mlp.c_proj.w", "prior.transformer._attn_mods.48.mlp.c_proj.b", "prior.transformer._attn_mods.48.ln_1.weight", "prior.transformer._attn_mods.48.ln_1.bias", "prior.transformer._attn_mods.49.attn.c_attn.w", "prior.transformer._attn_mods.49.attn.c_attn.b", "prior.transformer._attn_mods.49.attn.c_proj.w", "prior.transformer._attn_mods.49.attn.c_proj.b", "prior.transformer._attn_mods.49.ln_0.weight", "prior.transformer._attn_mods.49.ln_0.bias", "prior.transformer._attn_mods.49.mlp.c_fc.w", "prior.transformer._attn_mods.49.mlp.c_fc.b", "prior.transformer._attn_mods.49.mlp.c_proj.w", "prior.transformer._attn_mods.49.mlp.c_proj.b", "prior.transformer._attn_mods.49.ln_1.weight", "prior.transformer._attn_mods.49.ln_1.bias", "prior.transformer._attn_mods.50.attn.c_attn.w", "prior.transformer._attn_mods.50.attn.c_attn.b", "prior.transformer._attn_mods.50.attn.c_proj.w", "prior.transformer._attn_mods.50.attn.c_proj.b", "prior.transformer._attn_mods.50.ln_0.weight", "prior.transformer._attn_mods.50.ln_0.bias", "prior.transformer._attn_mods.50.mlp.c_fc.w", "prior.transformer._attn_mods.50.mlp.c_fc.b", "prior.transformer._attn_mods.50.mlp.c_proj.w", "prior.transformer._attn_mods.50.mlp.c_proj.b", "prior.transformer._attn_mods.50.ln_1.weight", "prior.transformer._attn_mods.50.ln_1.bias", "prior.transformer._attn_mods.51.attn.c_attn.w", "prior.transformer._attn_mods.51.attn.c_attn.b", "prior.transformer._attn_mods.51.attn.c_proj.w", "prior.transformer._attn_mods.51.attn.c_proj.b", "prior.transformer._attn_mods.51.ln_0.weight", "prior.transformer._attn_mods.51.ln_0.bias", "prior.transformer._attn_mods.51.mlp.c_fc.w", "prior.transformer._attn_mods.51.mlp.c_fc.b", "prior.transformer._attn_mods.51.mlp.c_proj.w", "prior.transformer._attn_mods.51.mlp.c_proj.b", "prior.transformer._attn_mods.51.ln_1.weight", "prior.transformer._attn_mods.51.ln_1.bias", "prior.transformer._attn_mods.52.attn.c_attn.w", "prior.transformer._attn_mods.52.attn.c_attn.b", "prior.transformer._attn_mods.52.attn.c_proj.w", "prior.transformer._attn_mods.52.attn.c_proj.b", "prior.transformer._attn_mods.52.ln_0.weight", "prior.transformer._attn_mods.52.ln_0.bias", "prior.transformer._attn_mods.52.mlp.c_fc.w", "prior.transformer._attn_mods.52.mlp.c_fc.b", "prior.transformer._attn_mods.52.mlp.c_proj.w", "prior.transformer._attn_mods.52.mlp.c_proj.b", "prior.transformer._attn_mods.52.ln_1.weight", "prior.transformer._attn_mods.52.ln_1.bias", "prior.transformer._attn_mods.53.attn.c_attn.w", "prior.transformer._attn_mods.53.attn.c_attn.b", "prior.transformer._attn_mods.53.attn.c_proj.w", "prior.transformer._attn_mods.53.attn.c_proj.b", "prior.transformer._attn_mods.53.ln_0.weight", "prior.transformer._attn_mods.53.ln_0.bias", "prior.transformer._attn_mods.53.mlp.c_fc.w", "prior.transformer._attn_mods.53.mlp.c_fc.b", "prior.transformer._attn_mods.53.mlp.c_proj.w", "prior.transformer._attn_mods.53.mlp.c_proj.b", "prior.transformer._attn_mods.53.ln_1.weight", "prior.transformer._attn_mods.53.ln_1.bias", "prior.transformer._attn_mods.54.attn.c_attn.w", "prior.transformer._attn_mods.54.attn.c_attn.b", "prior.transformer._attn_mods.54.attn.c_proj.w", "prior.transformer._attn_mods.54.attn.c_proj.b", "prior.transformer._attn_mods.54.ln_0.weight", "prior.transformer._attn_mods.54.ln_0.bias", "prior.transformer._attn_mods.54.mlp.c_fc.w", "prior.transformer._attn_mods.54.mlp.c_fc.b", "prior.transformer._attn_mods.54.mlp.c_proj.w", "prior.transformer._attn_mods.54.mlp.c_proj.b", "prior.transformer._attn_mods.54.ln_1.weight", "prior.transformer._attn_mods.54.ln_1.bias", "prior.transformer._attn_mods.55.attn.c_attn.w", "prior.transformer._attn_mods.55.attn.c_attn.b", "prior.transformer._attn_mods.55.attn.c_proj.w", "prior.transformer._attn_mods.55.attn.c_proj.b", "prior.transformer._attn_mods.55.ln_0.weight", "prior.transformer._attn_mods.55.ln_0.bias", "prior.transformer._attn_mods.55.mlp.c_fc.w", "prior.transformer._attn_mods.55.mlp.c_fc.b", "prior.transformer._attn_mods.55.mlp.c_proj.w", "prior.transformer._attn_mods.55.mlp.c_proj.b", "prior.transformer._attn_mods.55.ln_1.weight", "prior.transformer._attn_mods.55.ln_1.bias", "prior.transformer._attn_mods.56.attn.c_attn.w", "prior.transformer._attn_mods.56.attn.c_attn.b", "prior.transformer._attn_mods.56.attn.c_proj.w", "prior.transformer._attn_mods.56.attn.c_proj.b", "prior.transformer._attn_mods.56.ln_0.weight", "prior.transformer._attn_mods.56.ln_0.bias", "prior.transformer._attn_mods.56.mlp.c_fc.w", "prior.transformer._attn_mods.56.mlp.c_fc.b", "prior.transformer._attn_mods.56.mlp.c_proj.w", "prior.transformer._attn_mods.56.mlp.c_proj.b", "prior.transformer._attn_mods.56.ln_1.weight", "prior.transformer._attn_mods.56.ln_1.bias", "prior.transformer._attn_mods.57.attn.c_attn.w", "prior.transformer._attn_mods.57.attn.c_attn.b", "prior.transformer._attn_mods.57.attn.c_proj.w", "prior.transformer._attn_mods.57.attn.c_proj.b", "prior.transformer._attn_mods.57.ln_0.weight", "prior.transformer._attn_mods.57.ln_0.bias", "prior.transformer._attn_mods.57.mlp.c_fc.w", "prior.transformer._attn_mods.57.mlp.c_fc.b", "prior.transformer._attn_mods.57.mlp.c_proj.w", "prior.transformer._attn_mods.57.mlp.c_proj.b", "prior.transformer._attn_mods.57.ln_1.weight", "prior.transformer._attn_mods.57.ln_1.bias", "prior.transformer._attn_mods.58.attn.c_attn.w", "prior.transformer._attn_mods.58.attn.c_attn.b", "prior.transformer._attn_mods.58.attn.c_proj.w", "prior.transformer._attn_mods.58.attn.c_proj.b", "prior.transformer._attn_mods.58.ln_0.weight", "prior.transformer._attn_mods.58.ln_0.bias", "prior.transformer._attn_mods.58.mlp.c_fc.w", "prior.transformer._attn_mods.58.mlp.c_fc.b", "prior.transformer._attn_mods.58.mlp.c_proj.w", "prior.transformer._attn_mods.58.mlp.c_proj.b", "prior.transformer._attn_mods.58.ln_1.weight", "prior.transformer._attn_mods.58.ln_1.bias", "prior.transformer._attn_mods.59.attn.c_attn.w", "prior.transformer._attn_mods.59.attn.c_attn.b", "prior.transformer._attn_mods.59.attn.c_proj.w", "prior.transformer._attn_mods.59.attn.c_proj.b", "prior.transformer._attn_mods.59.ln_0.weight", "prior.transformer._attn_mods.59.ln_0.bias", "prior.transformer._attn_mods.59.mlp.c_fc.w", "prior.transformer._attn_mods.59.mlp.c_fc.b", "prior.transformer._attn_mods.59.mlp.c_proj.w", "prior.transformer._attn_mods.59.mlp.c_proj.b", "prior.transformer._attn_mods.59.ln_1.weight", "prior.transformer._attn_mods.59.ln_1.bias", "prior.transformer._attn_mods.60.attn.c_attn.w", "prior.transformer._attn_mods.60.attn.c_attn.b", "prior.transformer._attn_mods.60.attn.c_proj.w", "prior.transformer._attn_mods.60.attn.c_proj.b", "prior.transformer._attn_mods.60.ln_0.weight", "prior.transformer._attn_mods.60.ln_0.bias", "prior.transformer._attn_mods.60.mlp.c_fc.w", "prior.transformer._attn_mods.60.mlp.c_fc.b", "prior.transformer._attn_mods.60.mlp.c_proj.w", "prior.transformer._attn_mods.60.mlp.c_proj.b", "prior.transformer._attn_mods.60.ln_1.weight", "prior.transformer._attn_mods.60.ln_1.bias", "prior.transformer._attn_mods.61.attn.c_attn.w", "prior.transformer._attn_mods.61.attn.c_attn.b", "prior.transformer._attn_mods.61.attn.c_proj.w", "prior.transformer._attn_mods.61.attn.c_proj.b", "prior.transformer._attn_mods.61.ln_0.weight", "prior.transformer._attn_mods.61.ln_0.bias", "prior.transformer._attn_mods.61.mlp.c_fc.w", "prior.transformer._attn_mods.61.mlp.c_fc.b", "prior.transformer._attn_mods.61.mlp.c_proj.w", "prior.transformer._attn_mods.61.mlp.c_proj.b", "prior.transformer._attn_mods.61.ln_1.weight", "prior.transformer._attn_mods.61.ln_1.bias", "prior.transformer._attn_mods.62.attn.c_attn.w", "prior.transformer._attn_mods.62.attn.c_attn.b", "prior.transformer._attn_mods.62.attn.c_proj.w", "prior.transformer._attn_mods.62.attn.c_proj.b", "prior.transformer._attn_mods.62.ln_0.weight", "prior.transformer._attn_mods.62.ln_0.bias", "prior.transformer._attn_mods.62.mlp.c_fc.w", "prior.transformer._attn_mods.62.mlp.c_fc.b", "prior.transformer._attn_mods.62.mlp.c_proj.w", "prior.transformer._attn_mods.62.mlp.c_proj.b", "prior.transformer._attn_mods.62.ln_1.weight", "prior.transformer._attn_mods.62.ln_1.bias", "prior.transformer._attn_mods.63.attn.c_attn.w", "prior.transformer._attn_mods.63.attn.c_attn.b", "prior.transformer._attn_mods.63.attn.c_proj.w", "prior.transformer._attn_mods.63.attn.c_proj.b", "prior.transformer._attn_mods.63.ln_0.weight", "prior.transformer._attn_mods.63.ln_0.bias", "prior.transformer._attn_mods.63.mlp.c_fc.w", "prior.transformer._attn_mods.63.mlp.c_fc.b", "prior.transformer._attn_mods.63.mlp.c_proj.w", "prior.transformer._attn_mods.63.mlp.c_proj.b", "prior.transformer._attn_mods.63.ln_1.weight", "prior.transformer._attn_mods.63.ln_1.bias", "prior.transformer._attn_mods.64.attn.c_attn.w", "prior.transformer._attn_mods.64.attn.c_attn.b", "prior.transformer._attn_mods.64.attn.c_proj.w", "prior.transformer._attn_mods.64.attn.c_proj.b", "prior.transformer._attn_mods.64.ln_0.weight", "prior.transformer._attn_mods.64.ln_0.bias", "prior.transformer._attn_mods.64.mlp.c_fc.w", "prior.transformer._attn_mods.64.mlp.c_fc.b", "prior.transformer._attn_mods.64.mlp.c_proj.w", "prior.transformer._attn_mods.64.mlp.c_proj.b", "prior.transformer._attn_mods.64.ln_1.weight", "prior.transformer._attn_mods.64.ln_1.bias", "prior.transformer._attn_mods.65.attn.c_attn.w", "prior.transformer._attn_mods.65.attn.c_attn.b", "prior.transformer._attn_mods.65.attn.c_proj.w", "prior.transformer._attn_mods.65.attn.c_proj.b", "prior.transformer._attn_mods.65.ln_0.weight", "prior.transformer._attn_mods.65.ln_0.bias", "prior.transformer._attn_mods.65.mlp.c_fc.w", "prior.transformer._attn_mods.65.mlp.c_fc.b", "prior.transformer._attn_mods.65.mlp.c_proj.w", "prior.transformer._attn_mods.65.mlp.c_proj.b", "prior.transformer._attn_mods.65.ln_1.weight", "prior.transformer._attn_mods.65.ln_1.bias", "prior.transformer._attn_mods.66.attn.c_attn.w", "prior.transformer._attn_mods.66.attn.c_attn.b", "prior.transformer._attn_mods.66.attn.c_proj.w", "prior.transformer._attn_mods.66.attn.c_proj.b", "prior.transformer._attn_mods.66.ln_0.weight", "prior.transformer._attn_mods.66.ln_0.bias", "prior.transformer._attn_mods.66.mlp.c_fc.w", "prior.transformer._attn_mods.66.mlp.c_fc.b", "prior.transformer._attn_mods.66.mlp.c_proj.w", "prior.transformer._attn_mods.66.mlp.c_proj.b", "prior.transformer._attn_mods.66.ln_1.weight", "prior.transformer._attn_mods.66.ln_1.bias", "prior.transformer._attn_mods.67.attn.c_attn.w", "prior.transformer._attn_mods.67.attn.c_attn.b", "prior.transformer._attn_mods.67.attn.c_proj.w", "prior.transformer._attn_mods.67.attn.c_proj.b", "prior.transformer._attn_mods.67.ln_0.weight", "prior.transformer._attn_mods.67.ln_0.bias", "prior.transformer._attn_mods.67.mlp.c_fc.w", "prior.transformer._attn_mods.67.mlp.c_fc.b", "prior.transformer._attn_mods.67.mlp.c_proj.w", "prior.transformer._attn_mods.67.mlp.c_proj.b", "prior.transformer._attn_mods.67.ln_1.weight", "prior.transformer._attn_mods.67.ln_1.bias", "prior.transformer._attn_mods.68.attn.c_attn.w", "prior.transformer._attn_mods.68.attn.c_attn.b", "prior.transformer._attn_mods.68.attn.c_proj.w", "prior.transformer._attn_mods.68.attn.c_proj.b", "prior.transformer._attn_mods.68.ln_0.weight", "prior.transformer._attn_mods.68.ln_0.bias", "prior.transformer._attn_mods.68.mlp.c_fc.w", "prior.transformer._attn_mods.68.mlp.c_fc.b", "prior.transformer._attn_mods.68.mlp.c_proj.w", "prior.transformer._attn_mods.68.mlp.c_proj.b", "prior.transformer._attn_mods.68.ln_1.weight", "prior.transformer._attn_mods.68.ln_1.bias", "prior.transformer._attn_mods.69.attn.c_attn.w", "prior.transformer._attn_mods.69.attn.c_attn.b", "prior.transformer._attn_mods.69.attn.c_proj.w", "prior.transformer._attn_mods.69.attn.c_proj.b", "prior.transformer._attn_mods.69.ln_0.weight", "prior.transformer._attn_mods.69.ln_0.bias", "prior.transformer._attn_mods.69.mlp.c_fc.w", "prior.transformer._attn_mods.69.mlp.c_fc.b", "prior.transformer._attn_mods.69.mlp.c_proj.w", "prior.transformer._attn_mods.69.mlp.c_proj.b", "prior.transformer._attn_mods.69.ln_1.weight", "prior.transformer._attn_mods.69.ln_1.bias", "prior.transformer._attn_mods.70.attn.c_attn.w", "prior.transformer._attn_mods.70.attn.c_attn.b", "prior.transformer._attn_mods.70.attn.c_proj.w", "prior.transformer._attn_mods.70.attn.c_proj.b", "prior.transformer._attn_mods.70.ln_0.weight", "prior.transformer._attn_mods.70.ln_0.bias", "prior.transformer._attn_mods.70.mlp.c_fc.w", "prior.transformer._attn_mods.70.mlp.c_fc.b", "prior.transformer._attn_mods.70.mlp.c_proj.w", "prior.transformer._attn_mods.70.mlp.c_proj.b", "prior.transformer._attn_mods.70.ln_1.weight", "prior.transformer._attn_mods.70.ln_1.bias", "prior.transformer._attn_mods.71.attn.c_attn.w", "prior.transformer._attn_mods.71.attn.c_attn.b", "prior.transformer._attn_mods.71.attn.c_proj.w", "prior.transformer._attn_mods.71.attn.c_proj.b", "prior.transformer._attn_mods.71.ln_0.weight", "prior.transformer._attn_mods.71.ln_0.bias", "prior.transformer._attn_mods.71.mlp.c_fc.w", "prior.transformer._attn_mods.71.mlp.c_fc.b", "prior.transformer._attn_mods.71.mlp.c_proj.w", "prior.transformer._attn_mods.71.mlp.c_proj.b", "prior.transformer._attn_mods.71.ln_1.weight", "prior.transformer._attn_mods.71.ln_1.bias". 

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.