Are you putting up your Christmas decorations this weekend? Here's an SDXL fine-tune for inspiration: https://
replicate.com/fofr/sdxl-xmas
-houses
… And here's how to prompt it:
"A photo of an xmas decorated TOK house"
"A photo of an xmas decorated TOK submarine"
PROMPT ENGINEERING
-
SDXL Fine-tune for Christmas Decoration Inspiration
By
–
-
Building Retrieval Augmented Generation Chatbot with PDFs
By
–
Building a Retrieval Augmented Generation Chatbot If you are looking to learn how to build an end-to-end app to allows users to talk with their PDFs, check out this from @sophiamyang It covers: Ingestion
Prompting
Frontend Blog: https://
sophiamyang.medium.com/building-a-ret
rieval-augmented-generation-chatbot-d567a24fcd14
… -
Android Users Can Now Build No-Code AI Bots on Poe
By
–
Android users: You can now create bots on Poe!
— Poe (@poe_platform) 1 décembre 2023
Build no-code bots on top of the leading models, including GPT-4, Claude 2, DALL·E 3, SDXL, and Llama 2, and share them with the world. pic.twitter.com/duMKSNf5rFAndroid users: You can now create bots on Poe! Build no-code bots on top of the leading models, including GPT-4, Claude 2, DALL·E 3, SDXL, and Llama 2, and share them with the world.
-
Improve Your LLM: Training, Fine-tuning, and Prompt Engineering Guide
By
–
Learn the ins and outs of training from scratch, fine-tuning, and prompt engineering, including Few-Shot Learning and Retrieval Augmented Generation (RAG). Everything to enhance LLM performance, balancing quality, costs, and ease of use. https://
open.substack.com/pub/louisbouch
ard/p/how-to-improve-your-llm?r=25qlky&utm_campaign=post&utm_medium=web
… -
Optimize SEO in one click with our new SEO Analysis GPT
By
–
Optimize SEO in one click with our new SEO Analysis GPT Try it out here: https://
chat.openai.com/g/g-5nvVTD3I1-
seo-analysis-gpt
… Check out more GPTs built by God of Prompt: https://
godofprompt.ai/gpts #OpenAIDevDay #openai #chatgptai #customgpt #gpt4 #GPTstore #seomarketing #SEOExpert #seotips -
GPT-4 with good prompts beats fine-tuned Med-PaLM 2
By
–
Is prompt engineering dead? No, it’s SoTA. GPT-4 with good prompts (dynamic k-shot + self-generated CoT + choice-shuffled ensembles) beats Med-PaLM 2 on all nine of the MultiMedQA benchmarks it was fine-tuned for, without fine-tuning:
-
Smaller Open-Source LLMs Can Outperform Larger Commercial Models
By
–
Hot take: bigger isn't always better. Especially when we're talking about #LLMs. Smaller, faster #opensource LLMs can outperform much larger and more expensive commercial LLMs when #finetuned for a task. Try fine-tuning for free: https://
pbase.ai/40YVJRH. -
New Template Redacts Information Before LLM Processing
By
–
Check out this new template that redacts information before processing it with the LLM!
-
Improving LLMs: Choosing Between Training, Fine-tuning, and RAG
By
–
(new video) How to Improve your LLM? Find the Best & Cheapest Solution Learn when to choose between training from scratch, fine-tuning, (advanced) prompt engineering and Retrieval Augmented Generation (RAG) https://
youtu.be/pHv9SsE4Mb4
