trinsition/
minicpmv:latest

479 1 year ago

minicpm-llama3-2.5-8b-16-v With only 8B parameters, it surpasses widely used proprietary models like GPT-4V-1106, Gemini Pro, Claude 3 and Qwen-VL-Max and greatly outperforms other Llama 3-based MLLMs

1 year ago

4afe8c21f45c · 16GB

model
llama
·
8.03B
·
F16
params
{ "num_gpu": 12, "num_keep": 32, "num_predict": -2, "stop": [ "[<|eot_id|>"
template
{{ if .System }}<|start_header_id|>system<|end_header_id|>{{ .System }}<|eot_id|>{{ end }}{{ if .Pro

Readme

No readme