Djuunaa
djuna
AI & ML interests
None yet
Recent Activity
updated
a model
2 days ago
djuna/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-remap
updated
a model
2 days ago
djuna/DeepSeek-R1-Distill-Qwen-14B-abliterated-remap
Organizations
djuna's activity
chat template alet
#1 opened 2 days ago
by
djuna

New line after think tag
#3 opened 3 days ago
by
djuna

Different rms_norm_eps
2
#6 opened 4 months ago
by
djuna

How to use the model?
3
#1 opened 14 days ago
by
Omrisr

I think what you're doing here is really helpful
1
#2 opened 17 days ago
by
sometimesanotion

Need Example for inference code
#5 opened 25 days ago
by
djuna

Maybe not together?
#1 opened 25 days ago
by
djuna

Better than the first one?
#1 opened 25 days ago
by
djuna

Tokenizer problem
#2 opened 29 days ago
by
djuna

Evaluate new dolphin 3 r1 24B
1
#1097 opened about 1 month ago
by
djuna

Leaderboard benchmark?
2
#5 opened about 1 month ago
by
djuna

Tokenizer Details
7
#2 opened about 2 months ago
by
qingy2024

Update config.json
#1 opened about 1 month ago
by
djuna

Adding Evaluation Results
#1 opened about 2 months ago
by
djuna

Error: Unimplemented merge method sce
5
#35 opened about 2 months ago
by
xi0v

Upload necessary tokenizer
2
#2 opened about 2 months ago
by
djuna

feat: Choosable CLI, Custom Output Shard Size, LORA extraction
9
#30 opened 5 months ago
by
djuna

RYS with Qwen2.5
1
#5 opened 5 months ago
by
PSM24
Some sample
1
#3 opened 3 months ago
by
djuna

[MODELS] Discussion
643
#372 opened about 1 year ago
by
victor
