Models
GitHub
Discord
Turbo
Sign in
Download
Models
Download
GitHub
Discord
Sign in
deeokay
/
customllama
:latest
4
Downloads
Updated
1 year ago
Fine Tuning Llama3-8B-Instruct on a private dataset
Fine Tuning Llama3-8B-Instruct on a private dataset
Cancel
Updated 1 year ago
1 year ago
d21c3f1510cd · 4.9GB
model
arch
llama
·
parameters
8.03B
·
quantization
Q4_K_M
4.9GB
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr
254B
params
{ "repeat_penalty": 1.3, "stop": [ "<|start_header_id|>", "<|end_header_id|>
158B
Readme
Write
Preview
Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)