Fine Tuning Llama3-8B-Instruct on private dataset
1 Pull Updated 5 months ago
Updated 5 months ago
5 months ago
5db4df600278 · 4.0GB
model
archllama
·
parameters8.03B
·
quantizationQ3_K_M
4.0GB
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
Readme
No readme