Simulated W4Afp8 Quantization #331
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
for more information, see https://pre-commit.ci
WeiweiZhang1
approved these changes
Nov 28, 2024
n1ck-guo
approved these changes
Nov 28, 2024
auto_round/quantizer.py
Outdated
| self.orig_layer = orig_layer | ||
| self.device = device | ||
| self.enable_minmax_tuning = enable_minmax_tuning | ||
| self.enable_norm_bias_tuning = enable_norm_bias_tuning and orig_layer.bias is not None |
There was a problem hiding this comment.
enable_norm_bias_tuning and (orig_layer.bias is not None)
There was a problem hiding this comment.
not a must, right? is not should be calculated first
Signed-off-by: yiliu30 <[email protected]>
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Outdated suggestions cannot be applied.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.
for model_name in "/models/Meta-Llama-3.1-8B-Instruct" "/models/Meta-Llama-3-8B-Instruct"
do
CUDA_VISIBLE_DEVICES=$device
python3 -m auto_round
--model_name $model_name
--device 0
--act_bits 8
--group_size 128
--bits 4
--tasks "lambada_openai,hellaswag,winogrande,piqa,mmlu"
--eval_bs $eval_bs
--data_type "fp8_to_int_sym"
--act_data_type "fp8"
--disable_act_dynamic
--format "fake"
2>&1 | tee -a w4_fp8_act_static.txt
done