Downloads · 30 days
7
19% of all-time downloads
qwen3-0.6b-sft-hh
sorakritt/qwen3-0.6b-sft-hh
qwen3-0.6b-sft-hh is a machine learning model from sorakritt. 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 mit.
This model is an intermediate artifact from a ReMax alignment pipeline. It is the result of performing Supervised Fine-Tuning (SFT) on the base Qwen/Qwen3-0.6B-Base model.
All-time downloads
36
Public
Parameters
596M
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 99%
At a glance
- License
- mit
- Model type
- qwen3
- Access
- Public
- Created
- Oct 3, 2025
- Updated
- Oct 5, 2025
- SHA
- 81d185ae
Base models
Datasets
Model card
From the Hugging Face model README
SFT-tuned Qwen3-0.6B Model (Intermediate Artifact)
This model is an intermediate artifact from a ReMax alignment pipeline. It is the result of performing Supervised Fine-Tuning (SFT) on the base Qwen/Qwen3-0.6B-Base model.
Training Details
- Dataset: A subset of 30000 'chosen' examples from
Anthropic/hh-rlhf. - Epochs: 1
- Purpose: This model serves as the initial policy (
π_ref) for the ReMax alignment stage in the full training script. - Can be used in any pipeline where a SFT model is required.
- Type
- qwen3
- License
- mit
- Created
- Oct 3, 2025
- Updated
- Oct 5, 2025