Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
dnotitia 's Collections
4B SFT Experiments
Aether
Private Datasets (SFT - 2511)
Private Datasets (DPO - 2511)
Qwen3-ChatTemplate
DNA 2.1
DNA 2.0
DNA 2.0 (RC2)
DNA 2.0 (RC1)
DNA-R1
DNA 1.0
HMC
Smoothie Qwen3
Smoothie Qwen2.5
Private Models
Private Datasets (DNA 2.0)
Private Datasets (DNA 2.0 Evaluation)
Private Datasets (Qwen3 Korean)
Private Datasets (SFT)
Private Datasets (CoT)
Private Datasets (Only Answer)
Private Datasets (MATH)
Private Datasets (Reasoning, ko)
Private Datasets (Reasoning, en)
Private Datasets (CPT)
Private Datasets (DPO)
Private Datasets (Coding)
Private Datasets (RL, GRPO)
Private Datasets (Smoothie Qwen)

4B SFT Experiments

updated 16 days ago

Systematic SFT for Qwen3-4B. We explore diverse dataset compositions and training recipes to benchmark and improve performance across tasks.

Upvote
-

  • dnotitia/Qwen3-4B-Instruct-2507

    Text Generation • 4B • Updated Feb 9 • 691

  • dnotitia/Qwen3-4B-Thinking-2507

    Text Generation • 4B • Updated Feb 9 • 57

  • dnotitia/Qwen3-4B

    Text Generation • 4B • Updated Feb 9 • 63

  • dnotitia/Qwen3-4B-Base

    Text Generation • 4B • Updated Feb 9 • 1
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs