feat: modify rope for llama-3 and support llama-3.2 #131
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
aaronkl
approved these changes
Oct 10, 2024
whittle/models/gpt/model.py
Outdated
| from whittle.models.gpt.blocks import Block | ||
| from whittle.modules.embedding import Embedding | ||
| from whittle.modules.layernorm import LayerNorm | ||
| from whittle.modules.linear import Linear | ||
| from whittle.modules.rmsnorm import RMSNorm | ||
|
|
||
|
|
||
| class GPT(nn.Module): | ||
| class GPT(torch.nn.Module): |
There was a problem hiding this comment.
we import torch.nn above, so we can use nn.Module here
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Reference Issues/PRs
Closes #130 and #129
What does this implement/fix? Explain your changes.
Fixes rope for llama-3 models. Using whittle API in eval-harness we can now match llama-3.1-8B performance from huggingface api.
Minimal Example / How should this PR be tested?
Added test for llama 3.2