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
#230 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
๐OverallELO: 1,196
#311๐ฏ๐ตJapaneseELO: 1,003
#239๐จ๐ณChineseELO: 1,153
#316๐ฐ๐ทKoreanELO: 1,062
#243๐ฌ๐งEnglishELO: 1,229
#310frenchELO: 1,238
#230germanELO: 1,185
#247spanishELO: 1,171
#248russianELO: 1,158
#306๐ปCodingELO: 1,239
#313๐งฎMathELO: 1,191
#305โ๏ธCreative WritingELO: 1,159
#311๐Instruction FollowingELO: 1,179
#310๐ถ๏ธHard PromptsELO: 1,210
#313๐ฌMulti-TurnELO: 1,166
#307