The amount of non-deterministic behavior LLMs introduce makes me believe in techno-sorcery futures. Let's chant a verse, burn candles, perform data prayers and result purification rituals. Anything to get this endpoints perform predictable across different input
CODE
-
GPT-2 Reproduction with Increased Channel Size and Memory Optimization
By
–
We want to do a full GPT-2 repro, at channel size 1600 this is 2.1X higher C. And we'll want to ~max out batch dim to fit in memory too. So the "easy times" will be over soon.
-
Document Chunking Techniques for Better RAG Applications
By
–
But, How is Chunking Done? To create Better RAG applications, you need to know how to split or chunk the documents so you preserve the content while asking questions. Data Science Basics shows how to do this with LangChain https://
youtube.com/watch?v=tMwdl9
hFPns
… -
Chat with PDFs Using Local LLMs and Ollama RAG
By
–
How to chat with your PDFs using local Large Language Models [Ollama RAG] Covers loading PDFs with Unstructured, splitting that text data with RecursiveCharacterTextSplitter, creating embeddings with Ollama https://
youtube.com/watch?v=ztBJqz
BU5kc&t=1s
… -
Explore AI Tools Through daansan_ml’s Articles
By
–
Check out @daansan_ml
's articles for more information on AI tools -
Vector Space Mapping for Semantic Search and Fuzzy Matching
By
–
Similar concepts are mapped to nearby points in the high-dimensional vector space, enabling fuzzy matching and retrieval based on conceptual relevance rather than just keyword matching.
-
Vector Databases Enable Customized AI Applications with LLMs
By
–
Vector databases are key to building customised AI applications for businesses and individuals LLMs coupled with vector dbs can do wonders for the developers Learn more about vector databases from @daansan_ml
's insights -
CrowdLab: Python Library for Consensus Labels and Quality Scoring
By
–
This Python library works like magic! With a single line of code & the two matrices you see in the image below, I can find: – a consensus label
– quality score for individual & consensus labels
– overall quality score for each annotator Introducing CrowdLab! A weighted -
Passport.js Authentication Library Impact and Use Cases
By
–
“What has passportjs ever done for you”
