cs552-mlp
/

phi3-dpo

Model card Files Files and versions Community

Edit model card

Model Card for Model ID

DPO finetuned version of phi3-instruct-4k on student annotated preference data focusing on course content questions from EPFL curriculum (physics, math, cs).

Downloads last month: 3

Inference API

Unable to determine this model’s pipeline type. Check the docs .

Model tree for cs552-mlp/phi3-dpo

Base model

unsloth/Phi-3-mini-4k-instruct-bnb-4bit

Adapter

(22)

this model

Collection including cs552-mlp/phi3-dpo

Submitted Models

This collection includes base phi3-mini A) DPO aligned B) SFT on ARC train split (3 epochs) C) Quantised version of B) using GPTQ. • 4 items • Updated Jun 14