andiariffin/
llama-3.3-nemotron-super-v1.5-q4km:49b

30 1 month ago

High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.

49b
... /
params
e7f4213fc39a · 115B
{
"num_ctx": 131072,
"num_keep": 24,
"repeat_penalty": 1,
"stop": [
"<|eot_id|>"
],
"temperature": 0.6,
"top_p": 0.95
}