aha2025/
llama-joycaption-beta-one-hf-llava:Q8_0

1,477 4 months ago

oyCaption is an image captioning Visual Language Model (VLM) built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.

vision

4 months ago

94bd11542da3 · 9.4GB ·

model
llama
·
8.03B
·
Q8_0
projector
clip
·
434M
·
F16
params
{ "num_ctx": 4096, "num_keep": 4, "stop": [ "[INST]", "[/INST]" ] }
template
[INST] {{ if .System }}{{ .System }} {{ end }}{{ .Prompt }} [/INST]

Readme

No readme