Add Huggingface model zoo from community #1674
Closed
Conversation
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
Collaborator
|
Thank you for the PR. We will merge it soon. |
byshiue
added
triaged
Collaborator
|
Hi @matichon-vultureprime ,thanks for your contributing. We've merged your contribution into code base and will add you into contributor list. |
Merged
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Outdated suggestions cannot be applied.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.
According to [Feature Request: "Model Zoo" for quantization #1591],
this is our initial effort to create the Model Zoo.
The first model uploaded is Llama3-70b, AWQ Quantized.
I have identified several opportunities within the Model Zoo. I encountered a variety of configurations including PP_size, TP_size, KV_cache_type (fp16, fp8, int8), Group_size (64, 128), and Quantization algorithms (AWQ, SQ, FP8).
I will try to figure out the "proper" base configuration.
I have decided to use the lowest possible Group_size (to prevent the degradation of quantization) and set PP_size to 1.
Let's discuss if we can determine the "proper" configurations.