The Skywork o1 Open model series, developed by the Skywork team at Kunlun Inc. This groundbreaking release introduces a series of models that incorporate o1-like slow thinking and reasoning capabilities.
tools
8b
224 Pulls Updated 3 weeks ago
Updated 3 weeks ago
3 weeks ago
67c14ead13ce · 4.9GB
model
archllama
·
parameters8.03B
·
quantizationQ4_K_M
4.9GB
params
{
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
96B
license
The community usage of Skywork models require Skywork Community License. The Skywork models support
271B
system
You are Skywork-o1, a thinking model developed by Skywork AI, specializing in solving complex probl
433B
template
{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
{{- if .System }}
{{ .System
1.5kB
Readme
This is an uncensored version of Skywork/Skywork-o1-Open-Llama-3.1-8B 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.