Cohere For AI's language models trained to perform well across 23 different languages.
tools
8b
32b
54 Pulls Updated 4 days ago
Updated 5 days ago
5 days ago
fe7f158ee606 · 5.1GB
model
archcommand-r
·
parameters8.03B
·
quantizationQ4_K_M
5.1GB
params
{
"stop": [
"<|START_OF_TURN_TOKEN|>",
"<|END_OF_TURN_TOKEN|>"
]
}
81B
system
You are Aya, a brilliant, sophisticated, multilingual AI-assistant trained to assist human users by
263B
template
{{- if or .Tools .System }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>
{{- if .Tools }}# Safety Preamble
2.9kB
license
Creative Commons Attribution-NonCommercial 4.0 International Public
License with Acceptable Use Add
14kB
Readme
This is an uncensored version of CohereForAI/aya-expanse 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.