chore: add llama mlp_bias reading from hf_config #3476
Conversation
This file contains hidden or 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
juney-nvidia
added
Community want to contribute
juney-nvidia
changed the title
|
@WhatGhost Hi, thanks for the contribution. Pls do the sign-off of your own information to pass the DCO check firstly. Thanks |
Signed-off-by: Zihua Wu <[email protected]> Signed-off-by: whatghost <[email protected]>
Signed-off-by: whatghost <[email protected]>
WhatGhost
force-pushed
the
dev/llama_bias
branch
from
581ce15 to
c517c61
Compare
|
@juney-nvidia hi,i have sign-off follow the guide. |
|
@juney-nvidia Hi,Is there any work I need to do |
poweiw
added
Generic Runtime
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Outdated suggestions cannot be applied.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.
When i want to convert and build a llama model with attn_bias and mlp_bias. I noticed that in the config of trtllm's ckpt, the mlp bias is always false even i add mlp_bias in hf_model's config.
So i check the code of trtllm, I find the llama's config.py doesn't read mlp_bias param like the attn_bias.
So i add it.And the model can be converted and built correctly.