Intel's DeepSeek 67B model, trained on 2 trillion tokens in English and Chinese, has been open-sourced for research. It outperforms Claude-2, scoring 65 on a National High School Exam. The model has received top marks on the Hugging Face Leaderboard, thanks to Intel team members Haihao Shen and Kaokao Lv.
Intel's Latest Breakthrough: Neural Chat 7B Dominates the Hugging Face Leaderboard #AI #AItechnology #artificialintelligence #Customization #DirectPreferenceOptimizationalgorithm #HabanaGaudi2 #HuggingFaceTransformerspackage #Intel #LargeLanguageModel https://t.co/VNocvrtcLu https://t.co/caAX6gJ8cn
Our latest open source #AI model is getting top marks ✅ With groundbreaking efficiency and competitive performance, it's at the top of the @huggingface LLM leadership board, thanks to Intel team members Haihao Shen and Kaokao Lv. https://t.co/pcUHEXR4Nr
A day doesn't go by without a powerful open-source AI model drop. DeepSeek (67B) makes up for the open-source shortcomings - math and coding!! It beats Claude-2, scoring 65 on a National High School Exam. DeepSeek is from China and is proof that the Chinese don't need our LLM… https://t.co/VlpjEFnGZE https://t.co/chDvZ5YfRB
DeepSeek 67B model looks powerful. 📌 It has been trained on 2 trillion tokens in both English and Chinese. I 📌 DeepSeek 7B/67B Base and DeepSeek LLM 7B/67B Chat is open sourced for the research community. 📌 Commercial usage is permitted under some Licensing terms. 📌… https://t.co/SDok5HkBAb
DeepSeek 67B looks incredibly strong on benchmarks (like a llama-2 that can also write code) https://t.co/UuREZrHOMf