Mistral AI
Mistral: Mistral Nemo
mistralai/mistral-nemo
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.
Input
$0.029
/ 1M tokens
Output
$0.03
/ 1M tokens
Context window
131.07K
tokens
Limits
Context
131,072
tokens
Max output
16,384
13% of the context window
Parameters
12,247,782,400
Model facts
Author
Mistral AI
Tokenizer
Mistral
Modality
Text -> Text
License
Apache-2.0
Knowledge cutoff
2024-04-30
Created
Jul 19, 2024
Hugging Face
mistralai/Mistral-Nemo-Instruct-2407
Default generation parameters
temperature
0.3
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextOutput · Text
Generation controls
Frequency penaltyLogit biasLogprobsMax tokensMin pPresence penaltyRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobsTop p