RAG isn't dead, you just need a systematic workflow
Retrieval module, Augmentation module, and Generation module.
Fodev JEO
LATEST INVESTIGATIONS
Source audits & field notes
Top 6 ElasticSearch Use Cases
Curiosity: What makes Elasticsearch so versatile? How do organizations leverage its powerful search and analytics capabilities across different domain…
The giant leaps of open-source models for Vision Models
Curiosity: What insights can we retrieve from this? How does this connect to innovation in the field?
![["Workflow"]](/assets/img/llm/Llamma-finetune.jpeg)
Llamma Finetune case 와 RLHF 정리
Curiosity: How can we fine-tune Llama 3 8B to beat GPT-3.5? What makes Salesforce’s approach with Online Iterative RLHF so effective?
GPT4보다 LoRA를 적용한 결과가 전반적으로 낫더라?
Curiosity: Can fine-tuned smaller models outperform large general-purpose models on specific tasks?
Deep Dive into Transformers by Hand
A summary of the explanation of the Transformer model is as follows:.
Deep Dive into Self-Attention by Hand
Self-Attention is a method where each word in the input sequence evaluates its relationships with all other words to assign weights.
Deep Dive into LlaMA 3 by Hand
Deep Dive into LlaMA 3 by Hand ✍️ by Srijanie Dey, PhD May, 2024 Towards Data Science.
Deep Dive into Sora’s Diffusion Transformer (DiT) by Hand
Deep Dive into Sora’s Diffusion Transformer (DiT) by Hand ✍︎ by Srijanie Dey, PhD Apr, 2024 Towards Data Science.
Deep Dive into Vector Databases by Hand
Deep Dive into Vector Databases by Hand ✍︎ by Srijanie Dey, PhD Towards Data Science.
Search article titles, categories, and tags. Full text is searched when needed.
Type to search articles.