Hugging Face's logo

rhysjones
/
phi-2-orange

Text Generation
Transformers
Safetensors
phi-msft
custom_code
Inference Endpoints
Model card Files Community
6
phi-2-orange / README.md
rhysjones's picture
rhysjones
Updates to evaluations from Yet Another LLM Leaderboard results
fa70f50 verified
preview code
|
raw
history blame
2.12 kB
metadata
license: mit
datasets:
  - Open-Orca/SlimOrca-Dedup
  - migtissera/Synthia-v1.3
  - LDJnr/Verified-Camel
  - LDJnr/Pure-Dove
  - LDJnr/Capybara
  - meta-math/MetaMathQA
  - Intel/orca_dpo_pairs
  - argilla/ultrafeedback-binarized-preferences-cleaned

Phi-2 Orange

Phi-2 Orange

A two-step finetune of Phi-2, with a bit of zest.

First using a collection of broad training data:

And then a DPO finetune using:

Evaluations

Evaluations done using mlabonne's usefull Colab notebook llm-autoeval. Also check out the alternative leaderboard at Yet_Another_LLM_Leaderboard

Model AGIEval GPT4All TruthfulQA Bigbench Average
phi-2-orange 33.37 71.33 49.87 37.3 47.97
phi-2-dpo 30.39 71.68 50.75 34.9 46.93
dolphin-2_6-phi-2 33.12 69.85 47.39 37.2 46.89
phi-2 27.98 70.8 44.43 35.21 44.61