Models
Resources
Pricing
Chat
Status
Log in
Sign up
Models
Mistral
v02
predibase/Mistral-7B-Instruct-v0.2-dequantized
Hugging Face
Use via API
TEXT GENERATION
Concurrency Cost:
1
Model Size:
7B
Quant:
FP8
Ctx Length:
8k
Architecture:
Transformer
0.0K
Warm
Loading preview...
Full Model Card (README)