#mixtral-8x7b

#mixtral-8x7b

Mistral AI released Mixtral 8x7B, a large language model (LLM) that outperforms other models on benchmarks.

Mistral 8x7B is a sparse mixture of experts (SMoE) model with 46.7B parameters, but performs at the same speed and cost as smaller models. [ more ]

Mistral AI has developed a new AI language model called Mixtral 8x7B that reportedly matches OpenAI's GPT-3.5 in performance.

Mixtral 8x7B is a 'mixture of experts' model with open weights and can process a 32K token context window in multiple languages. [ more ]