Mistralai
Mistral: Mixtral 8x7B Instruct
Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion parameters. Instruct model fine-tuned by Mistral. #moe
| Specifications | |
|---|---|
| Provider | Mistralai |
| Input pricing | $0.54/M tokens |
| Output pricing | $0.54/M tokens |
| Context length | 33K tokens |
| Max output | 16K tokens |
| Input modalities | text |
| Output modalities | text |
| Tokenizer | Mistral |
| Knowledge cutoff | 2023-12-31 |
| Content moderated | No |
| HuggingFace | mistralai/Mixtral-8x7B-Instruct-v0.1 |
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p