Skip to content

download for 3.1 is broken #1069

@byjlw

Description

@byjlw

🐛 Describe the bug

The following commands will throw an exception.
python3 torchchat.py generate llama3.1 --prompt "write me a story about a boy and his bear"
python3 torchchat.py download llama3.1

onverting meta-llama/Meta-Llama-3.1-8B-Instruct to torchchat format...
Traceback (most recent call last):
  File "/Users/jessewhite/Documents/source/torchchat/torchchat.py", line 97, in <module>
    download_main(args)
  File "/Users/jessewhite/Documents/source/torchchat/download.py", line 198, in download_main
    download_and_convert(args.model, args.model_directory, args.hf_token)
  File "/Users/jessewhite/Documents/source/torchchat/download.py", line 91, in download_and_convert
    _download_hf_snapshot(model_config, temp_dir, hf_token)
  File "/Users/jessewhite/Documents/source/torchchat/download.py", line 55, in _download_hf_snapshot
    convert_hf_checkpoint(
  File "/Users/jessewhite/Documents/source/torchchat/.venv/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/jessewhite/Documents/source/torchchat/build/convert_hf_checkpoint.py", line 35, in convert_hf_checkpoint
    config = TransformerArgs.from_name(model_name)
             ^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: type object 'TransformerArgs' has no attribute 'from_name'

Versions

Collecting environment information...
PyTorch version: 2.5.0.dev20240814
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: macOS 14.1 (arm64)
GCC version: Could not collect
Clang version: 15.0.0 (clang-1500.1.0.2.5)
CMake version: version 3.30.2
Libc version: N/A

Python version: 3.11.8 (v3.11.8:db85d51d3e, Feb 6 2024, 18:02:37) [Clang 13.0.0 (clang-1300.0.29.30)] (64-bit runtime)
Python platform: macOS-14.1-arm64-arm-64bit
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Apple M3 Max

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] torch==2.5.0.dev20240814
[pip3] torchao==0.4.0+gite11201a
[conda] Could not collect

Metadata

Metadata

Assignees

Labels

bugSomething isn't working

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions