huihui_ai/
qwq-abliterated:32b-fp16

59.6K 2 months ago

QwQ is an experimental research model focused on advancing AI reasoning capabilities.

tools 32b

2 months ago

e2d8d53bc716 · 66GB

model
qwen2
·
32.8B
·
F16
params
{ "stop": [ "<|im_start|>", "<|im_end|>" ], "temperature": 0.6 }
template
{{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{- end }} {{- if .Too
license
Apache License Version 2.0, January 2004

Readme

This is an uncensored version of Qwen/QwQ created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

References

HuggingFace

Donation

You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge