Hackernews posts about Llama 3
Llama 3 is an AI-powered chatbot that uses pure NumPy to generate human-like conversations in a browser-based interface.
- Run Llama 3.3 70B Q40 on $1516 GPU 3.3 tok/s (github.com)
- Show HN: Tako, a Knowledge Search API (trytako.com)
- Show HN: AsianMOM – WebGPU Vision-LLM app that roasts you like ur mom in-browser (asianmom.kuber.studio)
- Show HN: KawaiiWatch – Making two LLM's fall in love in realtime (kawaii-watch.nightly.pw)
- With Its Llama API Service, Meta Platforms Becomes a Cloud (www.nextplatform.com)
- Ollama violating llama.cpp license for over a year (github.com)
- Show HN: Mirror AI – LLM agent that takes action, not just chat (themirrorai.com)
- Meta Llama 3 (llama.meta.com)
- Llama3 implemented from scratch (github.com)
- Llama 3 implemented in pure NumPy (docs.likejazz.com)
- Llama 3-V: Matching GPT4-V with a 100x smaller model and 500 dollars (aksh-garg.medium.com)
- Llama 3.1 (llama.meta.com)
- Llama-3.3-70B-Instruct (huggingface.co)
- Llama 3.1 Omni Model (github.com)
- Cost of self hosting Llama-3 8B-Instruct (blog.lytix.co)
- llama-fs: A self-organizing file system with llama 3 (github.com)
- Llama 3.1 in C (github.com)
- Run llama3 locally with 1M token context (ollama.com)
- Show HN: Llama 3.3 70B Sparse Autoencoders with API access (www.goodfire.ai)
- Ollama v0.1.33 with Llama 3, Phi 3, and Qwen 110B (github.com)
- Show HN: Tune LLaMa3.1 on Google Cloud TPUs (github.com)
- Llama 3 8B is almost as good as Wizard 2 8x22B (huggingface.co)
- Implementing LLaMA3 in 100 Lines of Pure Jax (saurabhalone.com)
- Longwriter – Increase llama3.1 output to 10k words (github.com)
- Hermes 3: The First Fine-Tuned Llama 3.1 405B Model (lambdalabs.com)