Djuunaa
djuna
AI & ML interests
None yet
Recent Activity
liked
a model
about 18 hours ago
NovaSky-AI/Sky-T1-32B-Flash
replied to
davidberenstein1957's
post
about 19 hours ago
Let's uncover the post-training dataset from DeepSeek-R1 with Magpie!
Pass pre-query tokens `<｜begin▁of▁sentence｜>User: `, let the model generate the rest.
We can get realistic examples!
Gist: https://gist.github.com/davidberenstein1957/3f20046ce57395a6aba13f8b4e956b59
replied to
davidberenstein1957's
post
about 20 hours ago
Let's uncover the post-training dataset from DeepSeek-R1 with Magpie!
Pass pre-query tokens `<｜begin▁of▁sentence｜>User: `, let the model generate the rest.
We can get realistic examples!
Gist: https://gist.github.com/davidberenstein1957/3f20046ce57395a6aba13f8b4e956b59
Organizations
Collections
1
spaces
6
models
91
djuna/MN-Chinofun-12B-4
Text Generation
•
Updated
•
21
•
2
djuna/MN-Chinofun-12B-4.1-Q6_K-GGUF
Updated
•
43
•
1
djuna/MN-Chinofun-12B-4.1
Text Generation
•
Updated
•
9
•
1
djuna/MN-Chinofun-12B-4-Q6_K-GGUF
Updated
•
78
•
1
djuna/Q2.5-KwK-7B-Q6_K-GGUF
Updated
•
17
djuna/Q2.5-Veltha-14B-0.5-AWQ-4bit
Updated
•
3
djuna/TEST-Q2.5-AA-Q8_0-GGUF
Updated
•
36
djuna/Q2.5-Veltha-14B
Text Generation
•
Updated
•
115
•
9
djuna/Q2.5-Veltha-14B-0.5
Text Generation
•
Updated
•
310
•
9
djuna/Q2.5-Veltha-14B-0.5-Q5_K_M-GGUF
Updated
•
22
•
1
datasets
None public yet