hyeogi
/

Yi-6b-dpo-v0.2

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Edit model card

Yi-6b-dpo

Model Details

Base Model: beomi/Yi-Ko-6B

Datasets

sampling and translate Open-Orca/SlimOrca
sampling and translate Anthropic/hh-rlhf

Benchmark

SOTA model under 7B as of Dec 20, 2023 (https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard).

Model	Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
hyeogi/Yi-6b-dpo-v0.2 (Ours)	52.63	41.72	52.96	46.69	52.38	69.42
hyeogi/Yi-6b-dpo-v0.1(Ours)	51.38	41.3	52.23	45.34	54.03	63.99
Minirecord/Mini_DPO_7b_01	50.47	48.29	54.68	46.7	47.78	54.9

Downloads last month: 1,592

Safetensors

Model size

6.18B params

Tensor type

FP16

·

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.