#GenerativeAI in #Metaverse Roblox builds in-house LLM, adds real-time AI translation to metaverse https://
cointelegraph.com/news/roblox-ai
-translation-llm-metaverse-languages
… via @cointelegraph
LLMS
-
Roblox Builds In-House LLM for Metaverse AI Translation
By
–
-
AI and VR enabling global medical diagnosis via MedPaLM in two years
By
–
AI + VR for medicine.
— AI Breakfast (@AiBreakfast) 6 février 2024
Doctors could diagnose and develop treatment plans for patients around the world.
And by Doctor I mean Google's MedPaLM in ~2 years. https://t.co/eTuBiSgwspAI + VR for medicine. Doctors could diagnose and develop treatment plans for patients around the world. And by Doctor I mean Google's MedPaLM in ~2 years.
-
Fine-tuning Language Models with Predefined Prompt Structures
By
–
Also, a question: When you fine-tune a model that had a predefined prompt structure, like, let's say, Mistral for instance with its [INST] Instruction [/INST] do you use that in the fine-tuning process too when you're feeding the new strings?
-
Guide complet : fine-tuner vos LLMs efficacement
By
–
Ready to #finetune but don't know where to start? We got you covered! Answers to your 4 biggest questions: When to fine-tune your #LLMs How to prepare your data What does it take to manage #infra How to reliably + #efficiently fine-tune
-
WebVoyager: End-to-End Web Agent with Large Multimodal Models
By
–
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models WebVoyager is a new kind of web-browsing agent, developed by Hongliang He, @wyu_nd
, et. al. Powered by large multi-modal models, like GPT-4V, it uses browser screenshots to conduct research, analyze -
RAG From Scratch: New Video Series on LLM Integration
By
–
RAG From Scratch: series focused on understanding the RAG landscape RAG is central for LLM application development, connecting LLMs to external data sources. But, the pace of innovation and new approaches makes it challenging to keep up. We're launching a new video
-
Free RAG Systems and AI Agents Webinar Next Week
By
–
Our free RAG systems, Chat LLMs, and AI Agents webinar is back next week. @bindureddy will kick-off with an exciting discussion about current developments within the LLM landscape before we provide a preview of our state-of-the-art ML and LLMOps platform. If you want to learn
-
Children Experience 50x More Data Than Largest Language Models
By
–
I've made that point before:
– LLM: 1E13 tokens x 0.75 word/token x 2 bytes/token = 1E13 bytes.
– 4 year old child: 16k wake hours x 3600 s/hour x 1E6 optical nerve fibers x 2 eyes x 10 bytes/s = 1E15 bytes. In 4 years, a child has seen 50 times more data than the biggest LLMs. x.com/tomosman/statu… -
Mixtral 8x7B Now Available for Poe Bot Creation
By
–
We’ve added Mixtral 8x7B as a base model for bot creation! All Poe users can now create prompt bots on Mixtral-8x7B-Chat, a chat fine-tuned version of one of the strongest open source models. We can’t wait to see what you build! pic.twitter.com/IYzQqCRRaq
— Poe (@poe_platform) 6 février 2024We’ve added Mixtral 8x7B as a base model for bot creation! All Poe users can now create prompt bots on Mixtral-8x7B-Chat, a chat fine-tuned version of one of the strongest open source models. We can’t wait to see what you build!