Aaron Feng
AaronFeng753
AI & ML interests
None yet
Recent Activity
new activity
2 days ago
Qwen/QwQ-32B:Too many "cross-validate" and "another method"
new activity
2 days ago
Qwen/QwQ-32B:Update QwQ collection
new activity
3 days ago
Qwen/QwQ-32B:复杂推理进入死循环
Organizations
None yet
AaronFeng753's activity
Too many "cross-validate" and "another method"
#43 opened 2 days ago
by
AaronFeng753
Update QwQ collection
#18 opened 3 days ago
by
AaronFeng753
复杂推理进入死循环
29
#21 opened 3 days ago
by
frankgxy
where is reasoning enhanced phi-4-mini?
1
#2 opened 10 days ago
by
AaronFeng753
ehristoforu/qwen2.5-test-32b-it
#1 opened 19 days ago
by
AaronFeng753
special token for imges
1
#29 opened 28 days ago
by
LHC88

[Bug] Only can use <think> once in the conversion
#2 opened about 1 month ago
by
AaronFeng753
fix typo
#1 opened about 1 month ago
by
AaronFeng753
https://huggingface.co/huihui-ai/Mistral-7B-Instruct-v0.3-abliterated
2
#616 opened about 1 month ago
by
AaronFeng753
Optimal settings for running Small-24b using Ollama?
9
#14 opened about 1 month ago
by
AaronFeng753
https://huggingface.co/huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
1
#608 opened about 1 month ago
by
AaronFeng753
What's your benchmark settings for DeepSeek-R1-Distill-Qwen-32B??
2
#2 opened about 1 month ago
by
AaronFeng753
the abliteration doesn't work
4
#2 opened about 1 month ago
by
CrestYao
Merge with 32b coder?
14
#2 opened about 2 months ago
by
RDson

R1 32b is much worse than QwQ ...
22
#6 opened about 2 months ago
by
mirek190
FuseO1-DeekSeekR1-QwQ-SkyT1-32B-Preview
2
#1 opened about 2 months ago
by
AaronFeng753
System Prompt
18
#2 opened about 2 months ago
by
Wanfq

IQ4_XS?
1
#1 opened about 2 months ago
by
AaronFeng753
Where is Phi-4?
#4 opened about 2 months ago
by
AaronFeng753
Eurus-2-7B-PRIME gguf
1
#1 opened 2 months ago
by
AaronFeng753