WizardLM-2 Open-Source Model Outperforms Proprietary Models on Benchmarks with Competitive Performance

Rohan Paul@rohanpaul_ai

2 years ago

Mixtral-8x22B and first instruct fine-tune, free for commercial use, native function calling, context window 64K, and open tokenizers for tools parsing and structured text. 🔥🔥 https://t.co/hn8MtNZVAQ

Clarifai@clarifai

2 years ago

.@MistralAI just announced Mistral 8x22B, their latest open model and we are excited to announce that the model is now available on the Clarifai Platform! 🎉 Key details of Mixtral 8x22B: • 64K token context window • Outperforms all open models • Fluent in English, French,… https://t.co/kEsC7xk23m

virat@virattt

2 years ago

I love open source. mixtral 8x22b is out and MMLU results seem strong. • 77.75% for mixtral 8x22b • 75.70% for command r+ • 69.90% for llama 2 70b Excited to test on my financial benchmarks. https://t.co/Iku813miBc