A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
7b
32b
831 Pulls Updated 4 weeks ago
Updated 4 weeks ago
4 weeks ago
ae64cdc10ec0 · 20GB
model
archqwen2
·
parameters32.8B
·
quantizationQ4_K_M
20GB
template
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
<|im_start|>{{ .R
275B
system
Your role as an assistant involves thoroughly exploring questions through a systematic long thinking
1.3kB
license
Apache License
Version 2.0, January 2004
http://www.apache.org/lice
10kB
Readme
This is an uncensored version of open-thoughts/OpenThinker-7B 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
Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin:
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge