223 1 week ago

Holo-3.1 vision-language computer-use agents by H Company. Locate UI elements and drive web, desktop & mobile automation from a screenshot — returns clicks in normalized [0,1000] coords. 0.8B & 4B, instruct & thinking variants, Q4_K_M/Q8_0. Apache 2.0.

vision tools 0.8b 4b
a902fcf4580c · 101B
{
"num_ctx": 8192,
"stop": [
"<|im_end|>",
"<|endoftext|>"
],
"temperature": 0,
"top_p": 1
}