Owen Arliawan's picture

Owen Arliawan

OwenArli

·

https://www.arliai.com/

AI & ML interests

Creator of Arli AI inference platform.

Recent Activity

new activity about 5 hours ago

Green-eyedDevil/Monika-106B:How did you get it to train with Axolotl on a Pro 6000?

liked a model about 17 hours ago

cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit

updated a model about 1 month ago

OwenArli/test-quant

View all activity

Organizations

New activity in Green-eyedDevil/Monika-106B about 5 hours ago

How did you get it to train with Axolotl on a Pro 6000?

#1 opened about 5 hours ago by

New activity in mistralai/Devstral-2-123B-Instruct-2512 about 2 months ago

Will we get a Instruct/Base version of this 123B model?

#2 opened about 2 months ago by

New activity in ArliAI/GLM-4.6-Derestricted-GPTQ-W4A16 about 2 months ago

Model download

#1 opened about 2 months ago by

New activity in ArliAI/GLM-4.5-Air-Derestricted about 2 months ago

Pls GPT oss

#4 opened 2 months ago by

New activity in ArliAI/GLM-4.5-Air-Derestricted 2 months ago

Add `transformers` as the library name

#3 opened 2 months ago by

New activity in Qwen/Qwen-Image 6 months ago

It's so unsafe that it can generate inappropriate adult content easily

#21 opened 6 months ago by

New activity in Ithanil/Llama-3_1-Nemotron-Ultra-253B-v1-W8A8-Dynamic 7 months ago

What was the reason for the skipped layers?

#2 opened 7 months ago by

New activity in QuixiAI/Qwen3-235B-A22B-AWQ 7 months ago

VLLM, SGLANG

#1 opened 9 months ago by

chriswritescode

New activity in justinjja/ERNIE-4.5-300B-A47B-PT-INT4-W4A16 7 months ago

Doesn't work in VLLM?

#1 opened 7 months ago by

New activity in ArliAI/QwQ-32B-ArliAI-RpR-v4 7 months ago

Qwen3

#2 opened 8 months ago by

Feedback/Appreciation (usage in SillyTavern chatbots)

#3 opened 8 months ago by

New activity in ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large 8 months ago

Question about formatting on SillyTavern.

#1 opened 8 months ago by

New activity in Qwen/Qwen3-235B-A22B-GPTQ-Int4 9 months ago

Cannot run with tensor parallel > 1. Might need padding like on Qwen2.5-72B?

#2 opened 9 months ago by

New activity in ArliAI/QwQ-32B-ArliAI-RpR-v3 9 months ago

add library_name tag for better discoverability on Hugging Face

#1 opened 9 months ago by

New activity in ArliAI/QwQ-32B-ArliAI-RpR-v3-GGUF 9 months ago

Qwen/QwQ-32B -> ArliAI/QwQ-32B-ArliAI-RpR-v3

#1 opened 9 months ago by

SaisExperiments

New activity in ArliAI/QwQ-32B-ArliAI-RpR-v1 10 months ago

Fix display of special tokens like <think> in readme

#3 opened 10 months ago by

New activity in qeternity/Qwen2.5-72B-Instruct-W8A8 about 1 year ago

Abouth w8a8 method

#1 opened about 1 year ago by

New activity in meta-llama/Llama-3.3-70B-Instruct about 1 year ago

Broken tokenizer.json file? 17.2mb on Llama 3.3 vs 9mb on Llama 3.1?

#16 opened about 1 year ago by

New activity in ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3 about 1 year ago

Add GPTQ quant link

#3 opened about 1 year ago by

New activity in noneUsername/Mistral-Nemo-Instruct-2407-W8A8-Dynamic-Per-Token-better about 1 year ago

Share quantization python script?

#1 opened about 1 year ago by