Recent Posts

• Stop Paying the OpenAI Tax: The Emerging Open-Source AI Stack
  by mchiangon 12/18/2024, 5:09:58 PM with 1 comment
• Bringing K/V context quantisation to Ollama
  by mchiangon 12/5/2024, 1:40:30 AM with 6 comments
• Providing Python functions as tools to models in Ollama
  by mchiangon 11/26/2024, 4:34:44 PM with 0 comments
• Meta Releases Llama 3
  by mchiangon 4/18/2024, 4:03:52 PM with 3 comments
• Building LLM poowered web apps using client-side technology
  by mchiangon 10/13/2023, 10:03:26 PM with 1 comment
• SeamlessM4T, a Multimodal AI Model for Speech and Text Translation
  by mchiangon 8/22/2023, 1:58:50 PM with 13 comments
• New llama.cpp format GGUF now merged
  by mchiangon 8/21/2023, 8:28:34 PM with 0 comments
• Llama 2 based WizardMath model to solve math problems with examples
  by mchiangon 8/17/2023, 5:51:27 PM with 0 comments
• FastViT: A Fast Hybrid Vision Transformer Using Structural Reparameterization
  by mchiangon 8/15/2023, 9:24:18 PM with 0 comments
• Llama 2 uncensored vs. GPT3.5 benchmarking
  by mchiangon 8/11/2023, 5:00:23 PM with 0 comments