Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
8,119 Pulls Updated 6 months ago
Updated 6 months ago
6 months ago
a8fb469ef6bd · 7.4GB
model
archllama
·
parameters13B
·
quantization4-bit
7.4GB
template
{{ .System }}
USER: {{ .Prompt }}
ASSISTANT:
45B
params
{"stop":["USER:","ASSISTANT:"]}
31B
Readme
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
CLI
Open the terminal and run ollama run wizard-vicuna
API
Example:
curl -X POST http://localhost:11434/api/generate -d '{
"model": "wizard-vicuna",
"prompt":"Why is the sky blue?"
}'
Memory requirements
- 13b models generally require at least 16GB of RAM