Add int8 models to Llama2 and Llama3 #1734
Merged
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
mattdangerw
reviewed
Aug 5, 2024
| @@ -25,6 +25,16 @@ | |||
| }, | |||
| "kaggle_handle": "kaggle://keras/llama2/keras/llama2_7b_en/1", | |||
| }, | |||
| "llama2_7b_en_int8": { | |||
| "metadata": { | |||
| "description": "LLaMA 2 7B Quantized Base model", | |||
There was a problem hiding this comment.
Maybe LLaMA 2 7B base model with weight quantized to int8.
There was a problem hiding this comment.
I have updated the description to follow Gemma's convention.
Additionally, I used "with activation and weights quantized to int8." to indicate that we are using dynamic int8 quantization instead of weights-only quantization.
WDYT?
james77777778
force-pushed
the
add-int8-models
branch
from
78b7862 to
61d1a5d
Compare
mattdangerw
approved these changes
Aug 6, 2024
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Outdated suggestions cannot be applied.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.
The
paramsis the number reported byModel.summary()which should be consistent with other models.All models can run inference using colab T4.
You can check out the outputs of
llama3_instruct_8b_en_int8from this colab:https://colab.research.google.com/drive/1KbUzNsY0906HFcn7FzRiBDtOtO-08msj?usp=sharing