Orion
Orion-zhen
AI & ML interests
Eco-friendly training using Tesla P4. Prefers (FSDP+)QLoRA.
Recent Activity
updated
a model
about 12 hours ago
Orion-zhen/our
new activity
6 days ago
Orion-zhen/phi-4-abliterated:mind doing phi 4 mini?
updated
a model
8 days ago
Orion-zhen/Fallen-Llama-3.3-R1-70B-v1-4.4bpw-h6-exl2
Organizations
Orion-zhen's activity
mind doing phi 4 mini?
6
#5 opened 9 days ago
by
0xDEADFED5

系统提示词,如何加入到角色卡中?
10
#1 opened 5 months ago
by
lklklk248
quantize parameters
5
#1 opened about 1 month ago
by
rastegar
do full r1
5
#4 opened about 2 months ago
by
drmcbride
Attempt Again?
4
#2 opened 3 months ago
by
User8213
Orion-zhen, You have a new abliteration job...
1
#2 opened 3 months ago
by
User8213
Question
1
#2 opened 3 months ago
by
so-anyway

Sync with official tokenizer_config.json
1
#3 opened 3 months ago
by
so-anyway

Do you do contract work for fine tunings and quantization?
1
#1 opened 3 months ago
by
rafa9
Mergrez / Megrez
1
#1 opened 3 months ago
by
rollercoasterX

How did you made this model?
1
#2 opened 3 months ago
by
Orion-zhen

What tensors have you modified?
5
#1 opened 3 months ago
by
Orion-zhen

Mind if I ask how you save apply the abliteration and save the model to disk?
2
#2 opened 3 months ago
by
Orion-zhen

ollama create fail
1
#2 opened 3 months ago
by
Laocaicai
back again - How'd you get Adam-Mini working with LLamafactory
2
#2 opened 3 months ago
by
Delta-Vector

Mind if i ask how you got KTO working with Unsloth
2
#1 opened 3 months ago
by
Delta-Vector

[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter

Model fails the strawberry test
15
#16 opened 4 months ago
by
Dev68
32b Coder
8
#5 opened 6 months ago
by
sm54
When 32b? 🫨
1
#9 opened 5 months ago
by
AlexBefest
