Back to Models
mistralai/mixtral-8x7b-instruct
Not Available
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
12/10/2023
32,768 tokens
#182 Text (french)
Specifications
Modalities
Input
text
Output
text
Supported Parameters
frequency_penalty
logit_bias
max_tokens
min_p
presence_penalty
repetition_penalty
response_format
seed
stop
temperature
tool_choice
tools
top_k
top_p
Max Output Tokens
16,384Leaderboard
Text
🏆OverallELO: 1,196
#266🇯🇵JapaneseELO: 1,002
#190🇨🇳ChineseELO: 1,154
#267🇰🇷KoreanELO: 1,063
#202🇬🇧EnglishELO: 1,229
#265frenchELO: 1,246
#182germanELO: 1,187
#208spanishELO: 1,175
#205russianELO: 1,158
#261💻CodingELO: 1,237
#268🧮MathELO: 1,189
#260✍️Creative WritingELO: 1,158
#266📝Instruction FollowingELO: 1,176
#265🌶️Hard PromptsELO: 1,209
#268💬Multi-TurnELO: 1,166
#262