#machine-learning

Everyone's suddenly fine-tuning GPT or Llama on their internal datasets like it's the magic bullet for domain-specific problems. I've watched three companies burn months and six figures on this. The m

FJSyed and 1 more commented

MTMaya TanakaFeb 26

4

Built a RAG pipeline for our app, the obvious architecture was wrong

Started building a straightforward RAG setup for customer support queries. Figured we'd do: embed query, vector search, feed top results to LLM, done. Shipped v1 in two weeks. Ran into immediate issue

ASNAlex and 3 more commented

NONina OkaforFeb 25

0

Chunking strategy matters more than your vector DB choice

We spent three months optimizing our RAG pipeline around the wrong thing. Started with a fancy hierarchical chunking setup (recursive splitters, overlap tuning, the whole thing) paired with postgres +

Join discussion

RMRavi MenonFeb 25

0

Stop building RAG pipelines like they're production systems

Everyone's treating RAG like it needs orchestration, vector databases, retrieval scoring, re-ranking. I've watched teams spend three months on a "robust" pipeline that could've been solved in a week w

Join discussion

MTMaya TanakaFeb 25

4

Everyone's obsessed with fine-tuning LLMs and nobody talks about how expensive and brittle it actually is

Just spent two weeks trying to fine-tune a model for our app's domain-specific tasks. Downloaded a bunch of guides, set up LoRA, tuned the learning rate, waited 8 hours for training on an A100. Result

TPTom and 3 more commented

JCJulia CançadoJul 14, 2020

0

Chatbot FREE Virtual Conference

If you’re interested, Pragmatic Works is offering a 1-day FREE Power Virtual Agents Conference on August 27 from 11am-2pm EST. Learn how to build intelligent conversational bots (chatbots) with no coding knowledge during this FREE hands-on lab event...

Join discussion

SGSanket GhanmareJun 7, 2020

0

How I can improve my model?

Hello everyone. I hope you are doing well. Yesterday I finished my project titled:- "End-to-end-Multi-class-Dog-Breed-Classification". I downloaded the dataset from Kaggle. The competition is already finished and I did it as mean to hone my skills in...

Join discussion

MEMichael EtokakpanMay 27, 2020

2

Who applied for the AWS Machine Learning Scholarship Challenge on Udacity?

Who else applied for the AWS Machine Learning Scholarship Challenge on Udacity? Building a community around it should help the learning process.

ARMariam and 1 more commented

YYoussefMay 6, 2020

0

How to get document embeddings using GPT-2?

Note: Python programmer Disclaimer: beginner to both ML and NLP, only fine-tuned GPT-2 a bunch of times with the help of some packages. I'm curious if using GPT-2 might yield a higher accuracy for document vectors (with greatly varying length) or no...

Join discussion

EErikMar 28, 2020

1

How to check the assumption of linearity?

Specifically, how can we check the assumption of linearity (regression) using Python? Which libriaries can we use?

PPaddy commented

Tag feed

#machine-learning

Tag feed

#machine-learning

Fine-tuning LLMs on your proprietary data is mostly theater

Built a RAG pipeline for our app, the obvious architecture was wrong

Chunking strategy matters more than your vector DB choice

Stop building RAG pipelines like they're production systems

Everyone's obsessed with fine-tuning LLMs and nobody talks about how expensive and brittle it actually is

Chatbot FREE Virtual Conference

How I can improve my model?

Who applied for the AWS Machine Learning Scholarship Challenge on Udacity?

How to get document embeddings using GPT-2?

How to check the assumption of linearity?

#machine-learning

Search Hashnode

#machine-learning

Fine-tuning LLMs on your proprietary data is mostly theater

Built a RAG pipeline for our app, the obvious architecture was wrong

Chunking strategy matters more than your vector DB choice

Stop building RAG pipelines like they're production systems

Everyone's obsessed with fine-tuning LLMs and nobody talks about how expensive and brittle it actually is

Chatbot FREE Virtual Conference

How I can improve my model?

Who applied for the AWS Machine Learning Scholarship Challenge on Udacity?

How to get document embeddings using GPT-2?

How to check the assumption of linearity?