Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
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-2.05BPW EXL3 quant of Nex-N2-Pro 397B.
markdown
-- A perplexity: 3.27108474-- B perplexity: 3.28186725-- A label in top-K:K = 1: 0.7133K = 2: 0.8113K = 3: 0.8532K = 4: 0.8767K = 5: 0.8923-- B label in top-K:K = 1: 0.7121K = 2: 0.8109K = 3: 0.8530K = 4: 0.8766K = 5: 0.8923-- Top-K agreement, A vs B:K = 1: 0.9714K = 2: 0.8759K = 3: 0.7432K = 4: 0.5986K = 5: 0.4631-- KL divergence (A, B): 0.00968818-- KL divergence (B, A): 0.00957145
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 detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information