A family of compact reasoning models, based off of the best 2B and 3B models, trained using improved DDP training code, no Unsloth.
Lunah
lunahr
AI & ML interests
None yet
Recent Activity
new activity
8 days ago
perplexity-ai/r1-1776:Any plans for distilled smaller models?
new activity
9 days ago
perplexity-ai/r1-1776:when distilled version?
new activity
15 days ago
lunahr/unavailablemodel-thea-v2-3b-50r:Do not file access requests
Organizations
None yet
Collections
2
models
15
lunahr/thea-pro-2b-100r
Text Generation
•
Updated
•
64
•
1
lunahr/thea-3b-50r-u1
Text Generation
•
Updated
•
9
lunahr/thea-3b-25r
Text Generation
•
Updated
•
212
•
1
lunahr/unavailablemodel-thea-v2-3b-50r
Text Generation
•
Updated
lunahr/thea-c-3b-25r
Text Generation
•
Updated
•
73
•
1
lunahr/thea-rp-3b-25r
Text Generation
•
Updated
•
206
•
1
lunahr/thea-3b-25r-adapter
Updated
•
7
•
1
lunahr/thea-rp-3b-25r-adapter
Updated
•
9
•
1
lunahr/thea-c-3b-25r-adapter
Updated
•
13
•
1
lunahr/Hermes-3-Llama-3.2-3B-abliterated
Text Generation
•
Updated
•
172
•
2