-
Notifications
You must be signed in to change notification settings - Fork 44
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat: Add deps to evaluate qLora tuned model (#312)
* Add support to load qLora tuned model in run_inference.py script Signed-off-by: Angel Luu <angel.luu@us.ibm.com> * Remove comment Signed-off-by: Angel Luu <angel.luu@us.ibm.com> * Disable gptq by default Signed-off-by: Angel Luu <angel.luu@us.ibm.com> * Remove the gptq-dev install in Dockerfile Signed-off-by: Angel Luu <angel.luu@us.ibm.com> * Rename gptq-dev package from gptq Signed-off-by: Angel Luu <angel.luu@us.ibm.com> * Add comments in run_inference.py Signed-off-by: Angel Luu <angel.luu@us.ibm.com> * Update device to cuda Signed-off-by: Angel Luu <angel.luu@us.ibm.com> * Add in the case that there's no adapter found Signed-off-by: Angel Luu <angel.luu@us.ibm.com> * Use torch.float16 for quantized Signed-off-by: Angel Luu <angel.luu@us.ibm.com> --------- Signed-off-by: Angel Luu <angel.luu@us.ibm.com>
- Loading branch information
Showing
2 changed files
with
59 additions
and
15 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters