QwQ is an experimental research model focused on advancing AI reasoning capabilities.
tools
32b
55.9K Pulls Updated 2 weeks ago
Updated 2 weeks ago
2 weeks ago
4388575b4992 · 20GB
model
archqwen2
·
parameters32.8B
·
quantizationQ4_K_M
20GB
params
{
"stop": [
"<|im_start|>",
"<|im_end|>"
],
"temperature": 0.6
}
77B
template
{{- if or .System .Tools }}<|im_start|>system
{{- if .System }}
{{ .System }}
{{- end }}
{{- if .Too
1.2kB
license
Apache License
Version 2.0, January 2004
11kB
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
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