bigscience
/

tr3m-1B3-pile-checkpoints

Model card Files Files and versions Community

tr3m-1B3-pile-checkpoints / global_step30000

History: 2 commits

bigscience-bot's picture

gelu_fast is the correct activation_function

8ffdbc4 over 2 years ago

config.json

1.78 kB

gelu_fast is the correct activation_function over 2 years ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.HalfStorage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
2.83 GB
LFS

add global_step30000 over 2 years ago