rixty/KoboldAI-Client
1
1
Fork 0
mirror of https://github.com/KoboldAI/KoboldAI-Client.git synced 2025-06-05 21:59:24 +02:00
Code Issues Projects Releases Wiki Activity

Merge pull request #180 from VE-FORBRYDERNE/patch

Browse Source 
Only enable TPU transpose optimization if loading from HF model
This commit is contained in:
henk717
2022-11-21 20:02:14 +01:00
committed by GitHub
parent f2077b8e58 9a3f0eaab2
commit 04d9172fcd
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tpu_mtj_backend.py
View File

@@ -1149,6 +1149,7 @@ def load_model(path: str, driver_version="tpu_driver0.1_dev20210607", hf_checkpo
params[param] = default_params[param] params[param] = default_params[param]
# Use an optimization that will allow us to avoid one extra transpose operation # Use an optimization that will allow us to avoid one extra transpose operation
if hf_checkpoint:
params["transposed_linear"] = True params["transposed_linear"] = True
# Load tokenizer # Load tokenizer