Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.

vision 11b 90b

9,115 11 hours ago

715415638c9c · 269B
{{- range $index, $_ := .Messages }}<|start_header_id|>{{ .Role }}<|end_header_id|>
{{ .Content }}
{{- if gt (len (slice $.Messages $index)) 1 }}<|eot_id|>
{{- else if ne .Role "assistant" }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{{ end }}
{{- end }}