Tag: #fine-tuning

한국어English日本語中文

← All posts

• The Claim of 100x Cheaper Is True Only When the Task Was Narrowed — Verification and Break-Even

  A case study published in August 2026 reports that a 4-billion-parameter-class open model, post-trained with reinforcement learning, matched frontier models on a retrieval task while cutting per-request cost by an order

  2026-08-09 · 8 min read #llm#cost#fine-tuning#retrieval#open-models

• The Conditions Under Which a 9B Fine-Tuned for 500 Dollars Beat the Frontier — And How Narrow They Are

  On July 28, 2026, a post scored 336 points on Hacker News. It reports that Fermisense trained Qwen3.5-9B with GRPO on roughly 500 dollars worth of GPU time and beat five frontier configurations — using the same tools and

  2026-07-31 · 11 min read #ai#llm#fine-tuning#reinforcement-learning#inference-cost

• RAG · Fine-Tuning · Long-Context — Which One for My Problem: What the Papers Actually Measured, and What No One Measured

  It's the most common question in LLM architecture, yet most answers are decision trees with no sources. This post answers only with what has been measured. That fine-tuning fails at injecting new knowledge has been measu

  2026-07-17 · 23 min read #rag#llm#fine-tuning#long-context#ai

• Do You Need a New Learning Rate When You Change LoRA Rank? — The Two Regimes μA (2026) Splits, and the Limits of That Evidence

  Two competing beliefs circulate in practice at the same time: that changing the rank in LoRA means you have to re-find the optimal learning rate, and that using 1/r scaling makes the learning rate independent of rank. Th

  2026-07-16 · 18 min read #llm#lora#fine-tuning#peft#training

• How to Become an AI Engineer in 2026 — LLMs, RAG, Agents, Evals, and a Career Roadmap

  The complete 2026 guide to becoming an AI Engineer. From how the role differs from ML Engineer and Data Scientist to LLM APIs, prompt engineering, RAG design, agents, LoRA fine-tuning, vLLM serving, evals-driven developm

  2026-07-02 · 26 min read #ai-engineer#career#llm#rag#ai-agents

• Training Vision LLMs — How to Teach Input and Output

  A vision-language model is trained in stages, from alignment pretraining to instruction fine-tuning. We organize what gets taught and how, from the angle of the training pipeline: vision encoder freezing strategy, data c

  2026-06-26 · 17 min read #mlops#vision-language-model#multimodal#training#instruction-tuning

• The 2026 Vision Model Development & Fine-Tuning Guide — CNN, ViT, DETR, SAM 2, VLMs and a Real Decision Tree

  Vision model development in 2026 is no longer 'grab a ResNet and call it a day.' Between CNNs, ViTs, DETR variants, SAM 2, and VLMs like LLaVA, Qwen-VL, Gemini Vision, and Claude Vision, your choice for the same photo ca

  2026-05-14 · 20 min read #computer-vision#vision-model#cnn#vit#detr

• MLX Deep Dive — Apple's ML Framework for Apple Silicon: Unified Memory, Lazy Graphs, and the Mac-Native Flow (2026 Hands-On)

  MLX is the array framework that Apple's ML team — the same people who previously built PyTorch and JAX — rewrote from scratch for Apple Silicon. The core thesis is one sentence: the M-series GPU shares RAM with the CPU,

  2026-05-14 · 19 min read #mlx#apple-silicon#ml-framework#unified-memory#metal

• Complete Guide to LLM Fine-tuning with Unsloth 2025: QLoRA, 4-bit Quantization, 2x Faster Training

  Everything about LLM fine-tuning with Unsloth! QLoRA/LoRA theory, 4-bit quantization (bitsandbytes), Unsloth 2x speed secret, Llama 3/Mistral/Qwen fine-tuning, data preparation, training config, VRAM optimization, GGUF/G

  2026-03-25 · 17 min read #unsloth#llm#fine-tuning#qlora#lora

• RAG vs Fine-tuning vs Prompt Engineering: The Complete Decision Framework

  A practical comparison of RAG, fine-tuning, and prompt engineering from a production engineering perspective, with a concrete decision framework, real cost calculations, and honest gotchas from building these systems in

  2026-03-18 · 7 min read #rag#fine-tuning#prompt-engineering#llm#ai-development

• Fine-tuning in Practice: Building Your Own Model with LoRA and QLoRA

  You don't need 7 H100s. With LoRA and QLoRA, you can fine-tune a 70B model on a single consumer GPU. A practical end-to-end guide with working code.

  2026-03-18 · 7 min read #fine-tuning#lora#qlora#llm#ai-development

• LLM Fine-tuning Complete Guide: Master LoRA, QLoRA, RLHF, and DPO

  A complete guide covering every LLM fine-tuning technique. From Full Fine-tuning to LoRA, QLoRA, RLHF, DPO, and Instruction Tuning — master them all with HuggingFace PEFT and hands-on examples.

  2026-03-17 · 21 min read #llm#fine-tuning#lora#qlora#rlhf

• Open-Source LLM Landscape Guide: Models, Tools, and Deployment in 2026

  A comprehensive guide to the open-source LLM ecosystem in 2026. Covers the leading model families (Llama, Mistral, Gemma, Qwen, DeepSeek), local inference tools (Ollama, llama.cpp, vLLM), fine-tuning techniques (LoRA, QL

  2026-03-17 · 20 min read #open-source#llm#llama#mistral#gemma

• LLM Fine-tuning Practical Guide: Efficient Model Adaptation with LoRA, QLoRA, and PEFT

  A comprehensive guide to LLM fine-tuning theory and practice. Covers LoRA low-rank decomposition principles, QLoRA 4-bit quantization techniques, PEFT library usage, dataset preparation strategies, and hyperparameter tun

  2026-03-13 · 10 min read #llm#fine-tuning#lora#qlora#peft

• Practical Guide to LLM Fine-Tuning: Efficient Domain Adaptation with LoRA, QLoRA, and PEFT

  An in-depth analysis of LoRA low-rank decomposition, QLoRA 4-bit quantized fine-tuning, and the Hugging Face PEFT library. Covers dataset preparation, hyperparameter tuning, evaluation metrics, comparison with full fine-

  2026-03-11 · 13 min read #llm#fine-tuning#lora#qlora#peft

• Practical LLM Fine-Tuning — Building Your Own Model with LoRA, QLoRA, and PEFT

  A practical guide to LLM fine-tuning. From the mathematical principles of LoRA to training large models on consumer GPUs with QLoRA, and leveraging the PEFT library — all with detailed code examples.

  2026-03-02 · 7 min read #llm#fine-tuning#lora#qlora#peft

• LoRA: Efficient Fine-tuning of Large Language Models — Paper Analysis

  A mathematical analysis of the core principles behind the LoRA (Low-Rank Adaptation) paper, along with practical implementation using HuggingFace PEFT.

  2026-03-01 · 17 min read #ai-papers#lora#fine-tuning#llm#peft

• Complete Analysis of the BERT Paper: How Bidirectional Transformers Changed the Landscape of NLP

  An in-depth analysis of Google BERT paper. We cover bidirectional pre-training through Masked Language Model (MLM) and Next Sentence Prediction (NSP), fine-tuning strategies, and the core principles of the architecture t

  2026-03-01 · 28 min read #bert#nlp#transformer#pre-training#fine-tuning