anpigon/
exaone-deep:latest

24 9 months ago

EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.

... /
params
f2c53de88926 · 93B
{
"num_ctx": 32768,
"repeat_penalty": 1,
"stop": [
"[|endofturn|]"
],
"temperature": 0.6,
"top_p": 0.95
}