EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.
2.4b
7.8b
32b
85 Pulls Updated 6 days ago
Updated 6 days ago
6 days ago
4936a5ec8430 · 19GB
model
archexaone
·
parameters32B
·
quantizationQ4_K_M
19GB
system
You are EXAONE model from LG AI Research, a helpful assistant.
62B
params
{
"repeat_penalty": 1,
"stop": [
"[|endofturn|]"
],
"temperature": 1
}
62B
template
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
{{ if eq .Role "s
375B
license
EXAONE AI Model License Agreement 1.1 - NC
This License Agreement (“Agreement”) is entered into
14kB
Readme
This is an uncensored version of LGAI-EXAONE/exaone-35 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.