Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

2BPW EXL3 quant of Nex-N2-Pro 397B.

markdown

-- A perplexity: 3.27149317
-- B perplexity: 3.62310984
-- A label in top-K:
K = 1: 0.7133
K = 2: 0.8114
K = 3: 0.8532
K = 4: 0.8767
K = 5: 0.8924
-- B label in top-K:
K = 1: 0.6874
K = 2: 0.7958
K = 3: 0.8399
K = 4: 0.8663
K = 5: 0.8840
-- Top-K agreement, A vs B:
K = 1: 0.8709
K = 2: 0.5901
K = 3: 0.3424
K = 4: 0.1836
K = 5: 0.0948
-- KL divergence (A, B): 0.22048885
-- KL divergence (B, A): 0.16824008

Model provider

cpral

Model tree

Base

nex-agi/Nex-N2-Pro

Quantized

this model

Modalities

Input

Video, Text, Image

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today