Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix RotaryEmbedding import in modify_gptneox #41

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix RotaryEmbedding import in modify_gptneox #41

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9f7ccfb
name RotaryEmbedding -> GPTNeoXRotaryEmbedding in utils_hh/modify_gpt…
benja-matic Jul 25, 2024
8669d62
update transformers version in install instructions
benja-matic Aug 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion h2o_hf/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@

```
pip install crfm-helm
pip install git+https://github.com/huggingface/transformers
pip install transformers==4.33
pip install lm-eval
```

Expand Down
4 changes: 2 additions & 2 deletions h2o_hf/utils_hh/modify_gptneox.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
from torch.cuda.amp import autocast
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss

from transformers.models.gpt_neox.modeling_gpt_neox import RotaryEmbedding, GPTNeoXAttention, apply_rotary_pos_emb
from transformers.models.gpt_neox.modeling_gpt_neox import GPTNeoXRotaryEmbedding, GPTNeoXAttention, apply_rotary_pos_emb


__all__ = ['convert_kvcache_gpt_neox_heavy_recent', 'GPTNeoXAttention_Mask']
Expand All @@ -34,7 +34,7 @@ def __init__(self, config):
),
)
self.register_buffer("masked_bias", torch.tensor(-1e9))
self.rotary_emb = RotaryEmbedding(
self.rotary_emb = GPTNeoXRotaryEmbedding(
self.rotary_ndims, config.max_position_embeddings, base=config.rotary_emb_base
)
self.register_buffer(
Expand Down