Downloads · 30 days
0
sathiiiii/polyalign-llama3.2-3b-zh-hdpo-critic-mlp
polyalign-llama3.2-3b-zh-hdpo-critic-mlp is a machine learning model from sathiiiii. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository contains the frozen-encoder, bucket-conditioned MLP critic bundle used to score Chinese HDPO preference pairs for llama323b.
Downloads · 30 days
0
Access
Public
Updated May 19, 2026
Repo size
3.5 MB
Likes
0
Public
Click a slice to open those files.
.pt3.5 MB · 54%
From the Hugging Face model README
This repository contains the frozen-encoder, bucket-conditioned MLP critic bundle used to score Chinese HDPO preference pairs for llama32_3b.
The policy-training HDPO JSONs were produced locally under:
data/chinese/hdpo_prepared/llama32_3b/llamafactory/