This repository has been archived by the owner on Aug 30, 2024. It is now read-only.
[Model Enabling] llama3-8b-instruct-chat Enabling #225
Conversation
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
Zhenzhong1
changed the title
Zhenzhong1
changed the title
kevinintel
approved these changes
Apr 18, 2024
|
please update support list |
a32543254
reviewed
Apr 19, 2024
| import faulthandler | ||
| import functools | ||
| import itertools | ||
| import json |
There was a problem hiding this comment.
how about use convert llama, rather than add new script.
There was a problem hiding this comment.
will merge to one file when refactoring.
zhentaoyu
approved these changes
Apr 19, 2024
There was a problem hiding this comment.
add <eot_id> processing for the end of the message in a turn, see https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/ and ggerganov/llama.cpp#6751 (comment).
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Type of Change
Supported llama3
Description
Expected Behavior & Potential Risk
N/A
How has this PR been tested?
Perf: -m 0 -C 0-55 m4
model.init(model_name, weight_dtype="int4", compute_dtype="int8")
model.generate(inputs, streamer=streamer, max_new_tokens=33, threads=56, ctx_size=1062, do_sample=False)
32 in 32 out
1024 in 32 out
model.init(model_name, weight_dtype="int4", compute_dtype="int8", scale_dtype="bf16")
Inference Screenshots:
FP32:
Q4_J:
Dependency Change?
N/A