InGoPenAIbykirouane AyoubBuilding a Custom Mixture of Experts Model for our Darija: From Tokenization to Text GenerationLets Build MOE model From scratch .Jul 25
InGenerative AIbysyromKnowledge Graph Extraction & Visualization with local LLM from Unstructured Text: a History exampleMotivation and contextApr 16
Rick GarciaUsing Groq, Mixtral 8x-7b, and Cursor IDE — A Simple HowToIf you’re not already using Cursor.sh, or you should be. It’s the AI-powered Developer IDE everyone’s talking about and the efficient…Mar 201Mar 201
U Vamsi KrishnaFormalizing Mixture of Experts from scratchThe most famous ground-breaking model, GPT-4, is speculated to be a Mixture of Experts (MoE) model. MoE consists of multiple expert models…Jun 16Jun 16
InTowards Data SciencebyMatthew GuntonUnderstanding the Sparse Mixture of Experts (SMoE) Layer in MixtralThis blog post will explore the findings of the “Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer” paper…Mar 211Mar 211
InGoPenAIbykirouane AyoubBuilding a Custom Mixture of Experts Model for our Darija: From Tokenization to Text GenerationLets Build MOE model From scratch .Jul 25
InGenerative AIbysyromKnowledge Graph Extraction & Visualization with local LLM from Unstructured Text: a History exampleMotivation and contextApr 16
Rick GarciaUsing Groq, Mixtral 8x-7b, and Cursor IDE — A Simple HowToIf you’re not already using Cursor.sh, or you should be. It’s the AI-powered Developer IDE everyone’s talking about and the efficient…Mar 201
U Vamsi KrishnaFormalizing Mixture of Experts from scratchThe most famous ground-breaking model, GPT-4, is speculated to be a Mixture of Experts (MoE) model. MoE consists of multiple expert models…Jun 16
InTowards Data SciencebyMatthew GuntonUnderstanding the Sparse Mixture of Experts (SMoE) Layer in MixtralThis blog post will explore the findings of the “Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer” paper…Mar 211
Mohor BFinetuning Mixtral 8x7b MoE using SQuAD2.0The finetuning was done on Google Colab using A100 GPU (with High RAM setting).Jun 14
Fireworks.aiFireworks Raises the Quality Bar with Function Calling Model and API ReleaseFireworks conducts alpha launch of our function calling model and API, with quality reaching GPT-4 and surpassing open-source modelsDec 20, 20231
