A fun model that tells you about it's neurotic internal thought process before responding
15 Pulls Updated 3 weeks ago
Updated 3 weeks ago
3 weeks ago
a984f2b86281 · 4.9GB
model
archllama
·
parameters8.03B
·
quantizationQ4_K_M
4.9GB
system
''
2B
params
{
"num_ctx": 4096,
"num_predict": 4096,
"stop": [
"<|start_header_id|>",
232B
template
<|start_header_id|>system<|end_header_id|>
Whatever the user says or asks will trigger intrusive tho
806B
Readme
The thoughts are in reflection tags, with the actual reply in an output tag
This uses the weights from @mychen76’s thought models.