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,...
Specifications
- Provider
- Mistral
- Type
- Open-source / open-weight
- Modality
- text->text
- Context window
- 131,072
- Knowledge cutoff
- 2024-04-30
- Released
- July 19, 2024
Capabilities
Input: textOutput: text
Strengths
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
