Fine Tuning Llama3-8B-Instruct on a private dataset
3 Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
d21c3f1510cd · 4.9GB
model
archllama
·
parameters8.03B
·
quantizationQ4_K_M
4.9GB
params
{
"repeat_penalty": 1.3,
"stop": [
"<|start_header_id|>",
"<|end_header_id|>
158B
template
{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .P
254B