As far as I know, you are not getting the base model through APIs, there is definitely fine-tuning and many guardrail instructions that are likely the result of prompting. Refusals to mess with copyright work, for example.
PROMPT ENGINEERING
-
Guided Outputs for LLMs and API Integration Tutorial
By
–
Discover how to use guided outputs for #LLMs, with a particular focus on LLMs and API. Start listening now at https://
linktr.ee/odsc by @_odsc #GenAI #AI #GenerativeAI #DataScience #DataScientists #MachineLearning #DeepLearning -
Training AI on Email Style: Better Than GPT-4
By
–
On emails: Have you tried training it on previous emails you've written/styles you want to replicate? I've noticed it can replicate the style of writing significantly better than GPT4
-
Faster Inference Engines Enable Real-Time Content Iteration in Software Development
By
–
Thanks to @freufreu for this fun demo showing that the advent of faster inference engines allows us to iterate on the entire content at every prompt during software development. https://
youtu.be/eR855VNPjhk -
New /describe Algorithm for Detailed Image Prompts Released
By
–
We're testing a new version of /describe today. Basically, show it an image and it'll try to describe it. This new algorithm is made to give longer, more detailed prompts, in the style of our community and is specifically tuned for our V6 models. Enjoy!
-
Dense Fine-Tuning Boosts MediSwift Biomedical Task Performance
By
–
(3/n) Dense fine-tuning and soft prompting enhance the performance of sparsely pre-trained MediSwift models on biomedical tasks (e.g., PubMedQA). This ensures high accuracy, thereby improving the efficiency-accuracy Pareto frontier. Pubmed QA leaderboard: https://
pubmedqa.github.io -
Extracting Full Logits from OpenAI API via Binary Search
By
–
for those who haven't heard about this:
openAI only gives you the top 5 logprobs per response (max). we (mostly @justintchiu
) came up with an algorithm to get logits from openAI. essentially for a different token (not top-5), u can binary search logit bias to see the minimal -
Prompt Length Strategy: Short Daily Use vs Detailed Consistency
By
–
Yep. I find for day-to-day stuff my prompts are shorter. I go 'mega' when I need a more consistent and repeatable output but often get away with a medium-sized prompt (1-2 paragraphs) otherwise.
-
Mastering NLP: From Foundations to Large Language Models
By
–
Mastering #NLProc from Foundations to #LLMs — Apply Advanced NLP Techniques to Solve Real World Business Problems: https://
amzn.to/3TawZDK (
@PacktPublishing release May 9. Pre-order now for price guarantee)
———
#DataScience #GenerativeAI #AI #MachineLearning #DeepLearning #GenAI -
New Extraction Guides for Structured Data from Unstructured Text
By
–
New extraction guides Reliably extracting structured data from unstructured text is one of the killer use-cases for LLMs. It's a fantastic way to bridge the gap between LLMs and traditional APIs and systems. We've put a lot of work on this lately, including an open