-
Notifications
You must be signed in to change notification settings - Fork 204
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
lm-eval for llama.cpp enhancement. #1543
base: main
Are you sure you want to change the base?
Conversation
⛈️ Required checks status: Has failure 🔴
Groups summary🔴 Format Scan Tests workflow
These checks are required after the changes to 🔴 Optimize Unit Test workflow
These checks are required after the changes to 🟢 NeuralChat Unit Test
These checks are required after the changes to 🟢 Engine Unit Test workflow
These checks are required after the changes to 🟢 Chat Bot Test workflow
These checks are required after the changes to Thank you for your contribution! 💜
|
for more information, see https://pre-commit.ci
usages:CPU
GPU
|
Type of Change
enable lm-eval for llama.cpp models
API not changed
Description
refer to the lm-eval official code and llama-cpp-python
improvements:
bos_id
for qwen models because thellama-cpp-python
doesn't addbos_id
successfully. Even though some changes for qwen, I still find that the tokenizer results are different between llama.cpp and huggingface/transformers. I will verify this further.llama-cpp-python
, I implement it with a custom class, which can accelerate the post-process.