We know that Jamba 1.5 models are the fastest, but the question is – how fast? @ArtificialAnlys tested our models to find out The image below shows the throughput for various models (with prompt length = 10K tokens). Jamba 1.5 models are a whole lot faster – and that speed
LLMS
-
Google Gemini API Caching: Explicit Payment Model Explained
By
–
Google Gemini also supports caching, using an explicit API where you pay for the time your content is cached: https://
ai.google.dev/gemini-api/doc
s/caching?lang=python
… -
Deepseek Introduces Fully Automated Prompt Caching Feature
By
–
BTW Deepseek also provides prompt caching — and theirs is fully automated, which is pretty cool!
-
Prompt Caching in Claude: Cost-Effective Token Optimization
By
–
Something that nearly everyone is sleeping on is the importance of prompt caching. We've just added support for it to Claudette, so @AnthropicAI caching is now *very* easy to use — cached tokens are 90% cheaper, and faster! Docs here: https://
claudette.answer.ai/#prompt-caching -
Fine-Tuning Your Own Llama 3 Model Series
By
–
I'm giving a new & improved series of talks about fine-tuning – @DataCamp
: live coding session, today at 11 AM ET (
https://
datacamp.com/webinars/fine-
tuning-your-own-llama-3-model
…) – @_odsc
: Open Data Science Conference, September 5-6 (
https://
odsc.com/europe/?utm_ca
mpaign=ODSCEurope&utm_content=304738063&utm_medium=social&utm_source=twitter&hss_channel=tw-3018841323
…) – @dctanner
: AI Engineer London Meetup, September 12 -
Generative AI Transforms Coding Speed and Developer Productivity
By
–
I tab tab tab. I can now code about any ML idea with VSCode and @MSFTCopilot while drinking an ice cold in a few hours. I remember many of these tasks used to take weeks for far better coders than me. Gen Software is remarkably transformative.
-
Scale Universal Self‑Consistency for Multi‑Step Prompting
By
–
Agree — a more fair baseline for big multi-step prompt pipelines would be universal self-consistency scaled up to the same inference budget
-
Academic Research Superprompt: Generate 4 Custom Research Prompts
By
–
Academic research superprompt: Choose one topic and this prompt will output 4 different prompts with the relevant author and field of study, later you will use each of that 4 prompts to generate your research outline. Source @shedntcare_ #ChatGPT #chatbots #chatgpt4
-
Push to talk in hands-free mode with Bluetooth
By
–
I like a push to talk but there is one more thing – last time I have used it in a hands-free mode with Bluetooth id didn't work well. ChatGPT was a bit more usable for this use case on the go. But I may need to test again if it changed
-
Prompt Engineering: Free Guide to Master 2024’s Most In-Demand Skill
By
–
The most in-demand skill of 2024: Prompt engineering. But most people don't know it. That's why I created this prompt engineering guide to help you master prompt engineering. Like + comment "Send" and I will DM the file to you for free. (Must be following me)