Improve prompts in a minute. Ensures effective communication. • Identify core message
• Simplify language
• Test with audience Read more: https://
godofprompt.ai/blog/how-to-im
prove-any-prompt
…
LLMS
-
How to Improve Prompts in a Minute – 3 Steps
By
–
-
Fine-tuning versus Prompting: Which Approach for Your Account?
By
–
Do you view my account as mostly fine-tuning, mostly prompting, or both?
-
Free AI Lessons and Prompts for Beginners at Lennon Labs
By
–
I want to add a free section to Lennon Labs with some solid and practical AI lessons and prompts. Anything on the beginner-intermediate side of AI you need help with? I’m open to suggestions – Keywords: LLMs ChatGPT Claude Gemini
-
Extending LLaMA 3 Context Window with PoSE Method
By
–
Starting on using PoSE to extend LLaMA 3's context window, with @winglian
's help. This one was really fun to work on. Eval loss started insanely high, let's see how far down we can get it. -
Engineering Managers Coding Again with LLM Assistance
By
–
I've talked to a few people who switched to engineering management roles years ago and are finding they can churn out little bits of working code again now because with LLM-assistance they can get something productive done in the much smaller amounts of available time they have
-
API Providers Extending Token Output Limits for Users
By
–
I believe that’s just a product decision by the API providers. No reason that can’t be extended. At HyperWrite, we often offer 5000 to 10,000 token outputs to users.
-
Elevate work with ChatGPT for efficient productivity in 2024
By
–
Elevate work with ChatGPT in 2024. AI boosts productivity efficiently. • Streamline communication
• Enhance decision-making
• Accelerate tasks Read more: https://
godofprompt.ai/blog/ways-to-u
se-chatgpt-for-work-in-2024
… -
Extending L3 70B context length with Unsloth on single A100
By
–
I almost always use (and LOVE) Axolotl… but wanted to try Unsloth to try to extend L3 70B's ctxlen w/ just one A100.
-
LLaMA 3-Instruct Dataset Format Structure Guide
By
–
Specifically, I have a dataset in the LLaMA 3-Instruct format:
“`
system {{ system_prompt }}user {{ user_message_1 }}assistant {{