@@ -73,7 +73,7 @@ CPU-only setup, as well as any GPU versions for applicable libraries like PyTorc
7373### Download model through MLCFlow Automation
7474
7575```
76- mlcr get,ml-model,mixtral --outdirname=<path_to_download> -j
76+ mlcr get,ml-model,mixtral,_r2-downloader,_mlc --outdirname=<path_to_download> -j
7777```
7878
7979### Get Checkpoint
@@ -102,13 +102,13 @@ rclone copy mlc-inference:mlcommons-inference-wg-public/mixtral_8x7b/mixtral-8x7
102102** Validation**
103103
104104```
105- mlcr get,dataset-mixtral,openorca-mbxp-gsm8k-combined,_validation --outdirname=<path to download> -j
105+ mlcr get,dataset-mixtral,openorca-mbxp-gsm8k-combined,_r2-downloader, _validation --outdirname=<path to download> -j
106106```
107107
108108** Calibration**
109109
110110```
111- mlcr get,dataset-mixtral,openorca-mbxp-gsm8k-combined,_calibration --outdirname=<path to download> -j
111+ mlcr get,dataset-mixtral,openorca-mbxp-gsm8k-combined,_r2-downloader, _calibration --outdirname=<path to download> -j
112112```
113113
114114- Adding ` _wget ` tag to the run command will change the download tool from ` rclone ` to ` wget ` .
@@ -307,4 +307,4 @@ For official submissions, 99% of each reference score is enforced. Additionally,
307307
308308## Automated command for submission generation via MLCFlow
309309
310- Please see the [ new docs site] ( https://docs.mlcommons.org/inference/submission/ ) for an automated way to generate submission through MLCFlow.
310+ Please see the [ new docs site] ( https://docs.mlcommons.org/inference/submission/ ) for an automated way to generate submission through MLCFlow.
0 commit comments