transformers
106b40c7
- Save dequantized models without the quantizer's weight conversions (#50271)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
18 hours ago
Save dequantized models without the quantizer's weight conversions (#50271) * Save dequantized weights under the model's own names * Drop the quantizer's conversions when a model is dequantized * Apply suggestion from @qgallouedec
References
#50271 - Save dequantized models without the quantizer's weight conversions
Author
qgallouedec
Parents
d0da3b84
Loading