The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. Mixtral-8x22B-v0.1 is a pretrained base model and therefore does not have any moderation mechanisms.

Evaluation Results

Open LLM Leaderboard Evaluation Results Detailed results can be found here

Metric	Value
Avg.	74.46
AI2 Reasoning Challenge (25-Shot)	70.48
HellaSwag (10-Shot)	88.73
MMLU (5-Shot)	77.81
TruthfulQA (0-shot)	51.08
Winogrande (5-shot)	84.53
GSM8k (5-shot)	74.15

Inference samples

Inference type	Python sample (Notebook)	CLI with YAML
Real time	text-generation-online-endpoint.ipynb	text-generation-online-endpoint.sh
Batch	text-generation-batch-endpoint.ipynb	coming soon

Sample inputs and outputs

Sample input

{
    "input_data": {
        "input_string": [
            "What is your favourite condiment?",
            "Do you have mayonnaise recipes?"
        ],
        "parameters": {
            "max_new_tokens": 100,
            "do_sample": true,
            "return_full_text": false
        }
    }
}

Sample output

[
  {
    "0": "\n\nDoes Hellmann's Mayonnaise Mallows really exist?\n\nThis is a difficult one because I want to pick Orkney ice cream which is unbelievable but I am also drawn to Hellmann's Mayonnaise Mallows (yeah, they really do exist) which I recently tried for the first time in California.\n\nThey were exactly how I expected them to taste – like marshmallows made from mayonnaise. I can'",
    "1": " I would imagine that the ingredients consist, at least in large part, of oil and cream [suggest edit]. However, I'm interested in baking mayonnaise into food, which means I'm worried that 50% of mayonnaise is just going to turn into oil and get absorbed by whatever it's cooked with [suggest edit] [suggest edit]. I thought that perhaps there might be a different recipe for mayonnaise which could be used specifically to with"
  }
]