4B SFT Experiments
Collection
Systematic SFT for Qwen3-4B. We explore diverse dataset compositions and training recipes to benchmark and improve performance across tasks.
•
7 items
•
Updated
AI & ML interests
Pioneering the Next Era of AI with Vector Intelligence
Recent Activity
likejazz
updated
a
collection
1 day ago
likejazz
updated
a
collection
2 days ago
likejazz
updated
a
collection
3 days ago
likejazz
updated
a
collection
4 days ago
likejazz
updated
a
collection
8 days ago
likejazz
published
8
models
8 days ago
dnotitia/Qwen3-0.6B-Base
Text Generation
•
0.6B
•
Updated
•
14
dnotitia/Qwen3-0.6B
Text Generation
•
0.8B
•
Updated
•
67
dnotitia/Qwen3-1.7B-Base
Text Generation
•
2B
•
Updated
•
5
dnotitia/Qwen3-1.7B
Text Generation
•
2B
•
Updated
•
22
dnotitia/Qwen3-4B-Base
Text Generation
•
4B
•
Updated
•
4
dnotitia/Qwen3-4B
Text Generation
•
4B
•
Updated
•
41
dnotitia/Qwen3-4B-Instruct-2507
Text Generation
•
4B
•
Updated
•
81
dnotitia/Qwen3-4B-Thinking-2507
Text Generation
•
4B
•
Updated
•
245
likejazz
updated
5
models
8 days ago