Allow loading of .safetensors through GPTQ-for-LLaMa#529
Merged
Conversation
Contributor
|
Yes, except we all have to re-quantize 100gb of models for this. |
Contributor
Author
|
Why would that be necessary? I mean, it's going to need to be done to support newer versions of GPTQ-for-LLaMa at some point, but that's not related to this PR. |
Owner
|
Thanks, this is handy! More updates on GPTQ will come after #530. |
Ph0rk0z
pushed a commit
to Ph0rk0z/text-generation-webui-testing
that referenced
this pull request
Apr 17, 2023
Allow loading of .safetensors through GPTQ-for-LLaMa
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Quantized models were hardcoded to only load .pt, but qwopqwop200's repo already works with .safetensors if we just pass in the other file extension.
With this PR, it looks for models in the order:
Seems to work fine, but I only tested on one janky model I ran through the quantizer myself.