A family of models based on Llama 3.2 including improved reasoning, trained with GaLoRE, rsLoRA and non-Unsloth code.
Piotr Zalewski
piotr25691
AI & ML interests
None yet
Organizations
None yet
models
12
piotr25691/thea-c-3b-25r
Text Generation
•
Updated
•
44
piotr25691/thea-rp-3b-25r
Text Generation
•
Updated
•
50
piotr25691/thea-3b-25r
Text Generation
•
Updated
•
176
•
1
piotr25691/thea-c-3b-25r-adapter
Updated
•
4
•
1
piotr25691/thea-rp-3b-25r-adapter
Updated
•
1
piotr25691/thea-3b-25r-adapter
Updated
•
1
piotr25691/SystemGemma2-27b-it
Text Generation
•
Updated
•
77
•
1
piotr25691/SystemGemma2-9b-it
Text Generation
•
Updated
•
27
piotr25691/SystemGemma2-2b-it
Text Generation
•
Updated
•
198
•
2
piotr25691/SystemGemma2-tokenizer
Updated