Username

noneUsername

·

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago

bottlecapai/ThinkingCap-Qwen3.6-27B

liked a dataset 21 days ago

QuixiAI/china-refusals

liked a model 2 months ago

trohrbaugh/gemma-4-31b-it-heretic-ara

View all activity

Organizations

None yet

New activity in huihui-ai/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated 8 months ago

Projected Abliteration

#1 opened 8 months ago by

New activity in huihui-ai/Qwen3-14B-abliterated 9 months ago

Can you train the abliterated model of qwen3-32b?

#2 opened about 1 year ago by

New activity in openai/gpt-oss-120b 11 months ago

gpt-oss is actually good. even on less common benchmark

#109 opened 11 months ago by

groupfairnessllm

New activity in Qwen/Qwen3-235B-A22B-Instruct-2507 12 months ago

An interesting phenomenon

#18 opened 12 months ago by

SimpleQA jumped from 12.2 to 54.3?

#4 opened 12 months ago by

New activity in noneUsername/Devstral-Small-2505-W8A8-Defective about 1 year ago

Details of Ability Loss

#1 opened about 1 year ago by

New activity in mistralai/Devstral-Small-2505 about 1 year ago

Thanks. Dedicated math and coding models is the only reasonable path forward.

#5 opened about 1 year ago by

New activity in alibaba-pai/DistilQwen2.5-DS3-0324-32B about 1 year ago

Is it the SFT model or the CogPO model in your paper?

#1 opened about 1 year ago by

New activity in noneUsername/Cydonia-24B-v2-W8A8-Defective over 1 year ago

Details of Ability Loss

#1 opened over 1 year ago by

New activity in huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated over 1 year ago

Thank you for your excellent contribution, however, this model seems to have some quality issues.

#1 opened over 1 year ago by

New activity in mistralai/Mistral-Small-24B-Instruct-2501 over 1 year ago

Anybody got it to run a quantized version with vLLM

#24 opened over 1 year ago by

This Mistral Small has FAR less knowledge than the last.

#5 opened over 1 year ago by

New activity in microsoft/phi-4 over 1 year ago

A heavily filtered corpus simply doesn't work.

#19 opened over 1 year ago by

I Don't Understand This Model

#9 opened over 1 year ago by

New activity in Qwen/QwQ-32B-Preview over 1 year ago

The censorship was so excessive that it led to a refusal to answer many non-sensitive questions as well

#3 opened over 1 year ago by

New activity in Xkev/Llama-3.2V-11B-cot over 1 year ago

With what open WebUI tools can it work?

#2 opened over 1 year ago by

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

Share quantization python script?

#1 opened over 1 year ago by

New activity in Qwen/Qwen-7B-Chat almost 3 years ago

请教Windows下csrc/layer_norm安不上的问题。

#20 opened almost 3 years ago by

存在的问题：1、bitsandbytes目前不支持windows，

#15 opened almost 3 years ago by

New activity in qbao775/PARARULE-Plus about 3 years ago

bad dataset at first data.

#1 opened about 3 years ago by