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
#234 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: 1,197
#316๐ฏ๐ตJapaneseELO: 1,003
#239๐จ๐ณChineseELO: 1,153
#320๐ฐ๐ทKoreanELO: 1,062
#247๐ฌ๐งEnglishELO: 1,229
#315frenchELO: 1,238
#234germanELO: 1,185
#247spanishELO: 1,172
#251russianELO: 1,159
#311๐ปCodingELO: 1,239
#318๐งฎMathELO: 1,191
#308โ๏ธCreative WritingELO: 1,159
#316๐Instruction FollowingELO: 1,179
#315๐ถ๏ธHard PromptsELO: 1,210
#318๐ฌMulti-TurnELO: 1,167
#312