huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix a typo

Browse Source 
Co-authored-by: drbh <david.richard.holtz@gmail.com>
This commit is contained in:
Daniël de Kok 2024-11-18 15:45:52 +01:00 committed by GitHub
parent e0018723fc
commit 3eb6c1ccf8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/text_generation_server/layers/compressed_tensors/w8a8_int.py
View File

@ -51,10 +51,10 @@ class W8A8IntLoader(WeightsLoader):
def scale_to_str(scale): def scale_to_str(scale):
return "static" if scale else "dynamic" return "static" if scale else "dynamic"
def symmetric_to_sting(symmetric): def symmetric_to_string(symmetric):
return "symmetric" if symmetric else "asymmetric" return "symmetric" if symmetric else "asymmetric"
return f"{self.__class__.__name__} (w8a8 int, input: dynamic/{symmetric_to_sting(self.input_symmetric)}, weight: {scale_to_str(self.load_weight_scale)}/symmetric))" return f"{self.__class__.__name__} (w8a8 int, input: dynamic/{symmetric_to_string(self.input_symmetric)}, weight: {scale_to_str(self.load_weight_scale)}/symmetric))"
def get_weights(self, weights: "Weights", prefix: str): def get_weights(self, weights: "Weights", prefix: str):
w = weights.get_tensor(f"{prefix}.weight", to_dtype=False) w = weights.get_tensor(f"{prefix}.weight", to_dtype=False)