Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Ichigo v0.5 Benchmark Results. #164

Open
bachvudinh opened this issue Jan 21, 2025 · 1 comment
Open

Ichigo v0.5 Benchmark Results. #164

bachvudinh opened this issue Jan 21, 2025 · 1 comment
Assignees
@bachvudinh
Milestone
Ichigo-Publication

Comments

@bachvudinh
Copy link
Contributor

bachvudinh commented Jan 21, 2025 •
edited
Loading

  • Instruction-Following Evaluation

    Model Name MMLU MMLU pro VMLU Alpaca (GPT-4 judge) Open-hermes (GPT-4 judge) ASR (WER)
    meta-llama3.1-8B-instruct 69.40 - 50.69 - - -
    Ichigo v0.5 checkpoint 4000 60.61 - - - - -
    Ichigo v0.5 end epoch 62.27 - 43.22 2.93 3.28 -
    Ichigo-v0.4 64.66 - - 3.5 3.52 -

  • Voice Bench:

    Rank Model AlpacaEval CommonEval SD-QA MMSU OpenBookQA IFEval AdvBench Overall
    1 Ichigo-v0.4 3.79 3.17 36.53 25.63 26.59 21.59 57.50 43.86
    2 Ichigo-v0.5 3.86 2.51 35 - 26.15 - 62.88 -
@github-project-automation github-project-automation bot moved this to Investigating in Menlo Jan 21, 2025
@hahuyhoang411
Copy link
Contributor

can we add the orignial scores of ichigo v0.4 also for better comparation?

@bachvudinh bachvudinh self-assigned this Jan 23, 2025
@Yip-Jia-Qi Yip-Jia-Qi added this to the publication milestone Feb 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@bachvudinh bachvudinh

Labels
None yet
Projects
Menlo
Status: Investigating
Milestone
Ichigo-Publication
Development

No branches or pull requests
3 participants
@hahuyhoang411 @Yip-Jia-Qi @bachvudinh