December Meetup
Dec
12
Tuesday
5PM to 8PM PDT
Main Stage Speakers
Will Stith
Founder at Decohere AI
Stable Video + SDXL Turbo experiments
View project page
Speaker details and project links
Combining new Stability AI models for fast image and video.
SDXL Turbo
Stable Video
Stability AI
Stable Diffusion XL
Open Source Models
David Hershey
Solutions Architect at Anthropic
Fine Tuning Mistral 7B on Magic Drafts
View project page
Speaker details and project links
Fine-tuning setup, data formatting, and tooling lessons learned.
Mistral 7B
GPT-4
Wei-Wei Wu
CEO at Momentic
Momentic
View project page
Speaker details and project links
How LLMs understand and act on complex web UIs.
Large Language Models
AI agents
End-to-end testing
Web automation
Natural Language Processing
Vik Korrapati
chief moondream officer at M87 Labs
Mixtral 8x7B
View project page
Speaker details and project links
Walkthrough of Mixtral's MoE architecture and efficient inference engineering.
Mixtral 8x7B
Mixture of Experts
Aaroh Mankad
Software Engineer at Plaid
Spoken Diagrams
View project page
Speaker details and project links
Applying conversational AI to generate complex system diagrams instantly.
No tech stack listed.
Kyle Corbitt
Founder at OpenPipe
Llama 2 vs Mistral (vs. GPT-3.5, OpenHermes 2.5, and Zephyr): comparing fine-tuning performance
View project page
Speaker details and project links
Head-to-head fine-tuning benchmarks reveal surprising model performance.
Llama 2
Mistral
OpenHermes 2.5
Zephyr
GPT-3.5
Scott Cummings
Creative Director at Sugarmilkgames
Harnessing LLM's For Hard Gameplay Dynamics
View project page
Speaker details and project links
Building game AI using RAG for dynamic NPC states.
Retrieval-Augmented Generation
Large Language Model
Artificial Intelligence
Game AI
NPC
Santiago Medina
Software Engineer at X Corp
Orca
View project page
Speaker details and project links
Learning Rust, Candle, and WebAssembly for local LLM inference.
Orca
Rust
WebAssembly
Candle
Hugging Face
