Owen Arliawan
OwenArli
AI & ML interests
Creator of Arli AI inference platform.
Recent Activity
new activity
14 days ago
Green-eyedDevil/Monika-106B:How did you get it to train with Axolotl on a Pro 6000?
liked
a model
15 days ago
cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit
updated
a model
about 2 months ago
OwenArli/test-quant
Organizations
How did you get it to train with Axolotl on a Pro 6000?
2
#1 opened 15 days ago
by
OwenArli
Will we get a Instruct/Base version of this 123B model?
👍
10
1
#2 opened 2 months ago
by
OwenArli
Model download
4
#1 opened 2 months ago
by
Lycaos
Pls GPT oss
2
#4 opened 3 months ago
by
ItzPingCat
Add `transformers` as the library name
#3 opened 3 months ago
by
ariG23498
It's so unsafe that it can generate inappropriate adult content easily
🤯
1
51
#21 opened 6 months ago
by
liougehooa
What was the reason for the skipped layers?
2
#2 opened 7 months ago
by
OwenArli
VLLM, SGLANG
7
#1 opened 9 months ago
by
chriswritescode
Doesn't work in VLLM?
🧠
1
1
#1 opened 7 months ago
by
OwenArli
Feedback/Appreciation (usage in SillyTavern chatbots)
👍
1
1
#3 opened 8 months ago
by
rohan-sircar
Question about formatting on SillyTavern.
1
#1 opened 8 months ago
by
R136a1
Cannot run with tensor parallel > 1. Might need padding like on Qwen2.5-72B?
😔
2
#2 opened 9 months ago
by
OwenArli
add library_name tag for better discoverability on Hugging Face
#1 opened 9 months ago
by
celinah
Qwen/QwQ-32B -> ArliAI/QwQ-32B-ArliAI-RpR-v3
2
#1 opened 10 months ago
by
SaisExperiments
Fix display of special tokens like <think> in readme
1
#3 opened 10 months ago
by
Mikael110
Abouth w8a8 method
3
#1 opened about 1 year ago
by
a-r-c
Broken tokenizer.json file? 17.2mb on Llama 3.3 vs 9mb on Llama 3.1?
➕
4
3
#16 opened about 1 year ago
by
OwenArli
Add GPTQ quant link
#3 opened about 1 year ago
by
GusPuffy
New activity in
noneUsername/Mistral-Nemo-Instruct-2407-W8A8-Dynamic-Per-Token-better
about 1 year ago
Share quantization python script?
4
#1 opened about 1 year ago
by
OwenArli