It will happen very soon. I need to build a serverless API infrastructure as a service to call LLMs locally on the instances.
LLMS
-
Large Language Models Available 24/7 Enable Unforeseen Possibilities
By
–
“There are going to be a bunch of things that are possible that we haven’t envisioned yet, because we haven’t imagined what you could do if you had a large language model available 24/7” @JonathanRoss321 said.
-
Open Source LLMs and the Path to AGI Achievement
By
–
@bindureddy Do you think AGI will certainly be achieved even with open source LLMs?
-
Maximizing ChatGPT and AI Insights with Ken Jee Podcast
By
–
Maximizing ChatGPT, AI Startups, Early days of Data science, and more AI Insights with @KenJee_DS – What's AI Podcast Ep. 23 Our conversation on YouTube: https://
youtu.be/TOD9-WyWExs
Listen on Spotify: https://
open.spotify.com/episode/68ODAV
tqyC44QK6e984V2y?si=MuHNw-EpQvOVME77yjF5EA
…
Listen on Apple Podcasts: https://
podcasts.apple.com/ca/podcast/max
imizing-chatgpt-ai-insights-with-ken-jee-whats-ai/id1675099708?i=1000635531387
… -
Chat Models True Capabilities Depend on Their Prompts
By
–
Using chat models without their prompts might not show their true capabilities though
-
Teaching templated strategies and intuition for problem-solving
By
–
More like teaching it a small arsenal of templated strategies for solving problems step-by-step, plus an intuition for which strategies to apply to which problems. It’s a system prompt so the goal is just to have it be generic; it’s not trying to be robust to bad instruction.
-
Microsoft’s Orca 2 13B beats 70B models with novel synthetic instruct data approach
By
–
Microsoft’s new 13B Orca 2 outperforms 70B models on many evals. Interesting synthetic instruct data:
1) try many detailed system prompts
2) generate answers using best prompt for each task
3) replace with generic system prompt in tuning demonstrations -
Orca 2: Open-Source Language Models 7B and 13B Parameters
By
–
“Orca 2 comes in two sizes (7 billion and 13 billion parameters); both are created by fine-tuning the corresponding LLAMA 2 base models on tailored, high-quality synthetic data. We open-source Orca 2 to encourage further research…”
-
Groq Invites Elon Musk to Test Its LPU Inference Engine
By
–
No word from @ElonMusk about running his #LLM on our #LPU ™ Inference Engine yet, but we've been trying to get his and @xAI's attention. You're right about one thing though – his #GenAI bot would achieve 10x better performance on #Groq. #GroqOn #BetterOnGroq #grokonGroq