The models `gemma3:12b`, `dolphin-llama3:8b`, and `llama2-uncensored:7b`— are primarily designed for text generation tasks (e.g., chat, completion) rather than sentence embeddings. They are not optimized for sentence transformation (i.e., generating dense vector representations for semantic similarity, clustering, or Retrieval-Augmented Generation). These models produce natural language outputs and lack the contrastive training or architecture (e.g., transformer-based sentence… Continue reading Generative Models vs Embedding Models in AI
A simple example of RAG
import ollama import chromadb # Sample documents documents = [ “Llamas are members of the camelid family meaning they’re pretty closely related to vicuñas and camels”, “Llamas were first domesticated and used as pack animals 4,000 to 5,000 years ago in the Peruvian highlands”, “Llamas can grow as much as 6 feet tall though the… Continue reading A simple example of RAG
AI fine tuning – How Lora works
LoRA (Low-Rank Adaptation) and QLoRA (Quantized LoRA) are techniques designed to fine-tune large language models efficiently, focusing on training fewer parameters while maintaining performance. What does LoRA do? LoRA injects small, trainable rank-decomposition matrices into the weights of the original pre-trained model. During fine-tuning, only these low-rank matrices are updated, while the original model weights… Continue reading AI fine tuning – How Lora works
Large Language Model Comparison (Oct 2025)
Large Language Model Comparison (Oct 2025) This comparison evaluates major open and commercial models — Llama 2, GPT‑J (6B), GPT‑3.5, Mistral 7B, Vicuna 13B, and Gemma 3 (12B) — across language quality, reasoning, and efficiency. Model Params Developer Open Source Strengths Limitations Overall Rank GPT‑3.5 ≈ 175B OpenAI No Most fluent and context‑aware; industry standard quality API‑only, closed model ★★★★★ Llama 2 (13B / 70B) 13B / 70B… Continue reading Large Language Model Comparison (Oct 2025)
AI Chat Roles
Summary of AI Chat Roles in Python APIs In AI conversational frameworks like OpenAI, Ollama, or LangChain, message roles define which entity a piece of text belongs to. These help the model maintain conversational structure and context. Role Purpose system Sets up the behavior, tone, and personality of the model. It gives core instructions that… Continue reading AI Chat Roles