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

initialize zp, scale loaded from HF quantizer, applying quant_config #84

Closed
wants to merge 2 commits into from
Closed

initialize zp, scale loaded from HF quantizer, applying quant_config #84

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4b514a5
initialize zp, scale loaded from HF quantizer, applying quant_config
horheynm Jun 14, 2024
6fd15bf
Merge branch 'main' into init-model-load
Jul 10, 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
9 changes: 8 additions & 1 deletion src/compressed_tensors/compressors/model_compressor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,7 +269,14 @@ def decompress(self, model_path: str, model: Module):
self._replace_weights(dense_gen, model)

def update_status(module):
module.quantization_status = QuantizationStatus.FROZEN
import torch

first_param_dtype = next(model.parameters()).dtype
if first_param_dtype == torch.float16:
# loading unquantized model
module.quantization_status = QuantizationStatus.INITIALIZED
else:
module.quantization_status = QuantizationStatus.FROZEN

model.apply(update_status)
setattr(model, QUANTIZATION_CONFIG_NAME, self.quantization_config)
Expand Down
Loading