#Fine-Tuning

Articles about Fine-Tuning — exploring patterns, best practices, and real-world implementations in production systems.

11 posts tagged with fine-tuning. ← All posts

#A2A (14)#ADK (8)#AG-UI (6)#AI (9)#AI Agents (303)#AI Architecture (10)#AI Cost (10)#AI Cost Optimization (8)#AI Engineering (160)#AI Governance (28)#AI Red Teaming (9)#AI Research (9)#AI Safety (6)#AI Security (21)#AI in Production (12)#AML (3)#API Design (10)#API Security (8)#APIs (47)#AWS (17)#Accounting (9)#Agent Skills (3)#Agentic AI (24)#Agentic Commerce (12)#Agentic RAG (8)#Agents (4)#Amazon Bedrock (8)#Architecture (36)#Audit (3)#Authentication (10)#Authorization (3)#Automation (6)#Azure (11)#Azure AI Foundry (9)#Backend Engineering (267)#BigQuery (6)#CI/CD (8)#Capital Markets (14)#Card Payments (12)#Cards (13)#Career (7)#Checkpointing (4)#Claude Code (8)#Cloud (3)#Cloud Architecture (3)#Code Review (8)#Collaboration (4)#Communication (4)#Compliance (51)#Computer Networking (8)#Concurrency (25)#Consulting (3)#Context Engineering (10)#Cost Optimisation (5)#Credit (14)#Credit Risk (14)#CrewAI (8)#Crypto (12)#Cryptocurrency (12)#Custody (9)#DSPy (8)#Data (4)#Data Engineering (4)#Data Structures (8)#Databases (33)#Deployment (3)#DevOps (9)#DevSecOps (11)#Developer Experience (5)#Distributed Systems (88)#Documentation (3)#Edge AI (8)#Embeddings (14)#Engineering (7)#Engineering Culture (3)#Engineering Practices (16)#Evaluation (44)#Event-Driven Architecture (8)#FREE-AI (8)#FX (5)#FinOps (23)#FinTech (6)#Financial AI (14)#Financial Systems (129)#Fine-Tuning (11)#Fintech (131)#Flutter (8)#Foreign Exchange (5)#Forward Deployed Engineer (8)#Forward Deployed Engineering (8)#Fraud (10)#Function Tools (5)#GCP (5)#Gemma (4)#Go (220)#Google ADK (36)#Governance (55)#Granite (6)#GraphQL (3)#Guardrails (24)#HIPAA (3)#HTTP (3)#Harness Engineering (8)#Hugging Face (8)#Human-in-the-Loop (8)#IBM watsonx (8)#Identity (11)#Integration (3)#Interfaces (3)#KYC (11)#KYC and AML (12)#Kafka (10)#Kubernetes (9)#LLM (5)#LLM Inference (8)#LLMs (110)#LangChain (8)#LangGraph (11)#Ledger (12)#Lending (14)#LlamaIndex (8)#MCP (22)#MLOps (30)#Machine Learning (13)#Markets (4)#Memory (13)#Memory Management (4)#Microservices (3)#Microsoft Agent Framework (150)#Middleware (6)#Migration (9)#Monitoring (3)#Multi-Agent (10)#Multi-Agent AI (14)#Multi-Agent Systems (70)#Multimodal (3)#NIM (5)#NVIDIA (8)#OAuth (3)#OWASP (7)#Observability (43)#On-Device AI (8)#Open Source (6)#OpenTelemetry (5)#Opinion (6)#Orchestration (10)#Payment Rails (16)#Payments (54)#Performance (29)#Platform Engineering (9)#Privacy (4)#Privacy Engineering (3)#Product (4)#Production (6)#Programming (10)#Programming Languages (16)#Prompt Engineering (64)#Prompt Injection (6)#Protocols (9)#Providers (4)#Pydantic AI (8)#Python (142)#Quality (3)#RAG (58)#RBI (3)#REST (5)#Rails (16)#Reconciliation (3)#RegTech (8)#Regulation (9)#Reliability (45)#Resilience (3)#Responsible AI (5)#Retrieval (3)#Risk (13)#Rust (16)#SRE (20)#Scalability (3)#Security (80)#Self-Evolving Agents (16)#Sessions (3)#Settlement (9)#Software Architecture (35)#Software Engineering (138)#Spanner (4)#Strands (8)#Streaming (25)#Structured Output (4)#System Design (32)#Systems Programming (16)#Testing (34)#Tool Use (21)#Tools (3)#Trading (8)#Treasury (6)#Type System (3)#Type Systems (3)#Vector Databases (21)#Vector Search (11)#Web Development (6)#Workflows (14)#gRPC (5)#smolagents (8)
Pratik Dhanave · ·6 min read

Fine-Tuning in Production

Training a good fine-tune is the easy half. Running it in production — deciding it's even worth it, serving adapters efficiently, keeping it from going stale as base models leap ahead, and re-tuning as your needs shift — is where fine-tuning becomes an ongoing commitment rather than a one-time project. This is the reality check that closes the series.

Training a good fine-tune is the easy half. Running it in production — deciding it's worth it, serving adapters efficiently, keeping it from going stale as base models leap ahead, and re-tuning — is where fine-tuning becomes an ongoing commitment.

#Fine-Tuning#LLMs#MLOps#AI Engineering
Pratik Dhanave · ·6 min read

Evaluating a Fine-Tuned Model

A fine-tune that looks great on a handful of hand-picked prompts can be quietly broken — overfit to your training data, worse than the base model you started from, or catastrophically forgetful of skills it used to have. Without real evaluation you can't tell, and shipping a fine-tune you haven't measured is shipping a guess.

A fine-tune that looks great on a handful of prompts can be quietly broken — overfit, worse than the base model, or catastrophically forgetful. Without real evaluation you can't tell, and shipping a fine-tune you haven't measured is shipping a guess.

#Fine-Tuning#LLMs#Evaluation#MLOps#AI Engineering#Prompt Engineering
Pratik Dhanave · ·6 min read

Alignment: RLHF and DPO

Supervised fine-tuning teaches a model to produce a correct answer; alignment teaches it to produce the answer people actually prefer. That shift — from "right" to "better" — is what turned raw language models into helpful assistants, and the move from RLHF's complex machinery to DPO's direct approach made it something ordinary teams can do.

Supervised fine-tuning teaches a model to produce a correct answer; alignment teaches it to produce the answer people actually prefer. That shift turned raw models into helpful assistants, and the move from RLHF to DPO made it something ordinary teams can do.

#Fine-Tuning#LLMs#AI Engineering#AI Research
Pratik Dhanave · ·6 min read

Data: The Real Determinant

You can pick the perfect technique, tune every hyperparameter, and rent the best GPU — and still get a worse model than you started with, because your dataset was mediocre. Fine-tuning quality is decided overwhelmingly by data quality, and a few hundred excellent examples beat tens of thousands of sloppy ones. This is the post that actually determines whether your fine-tune works.

You can pick the perfect technique and rent the best GPU, and still get a worse model, because your dataset was mediocre. Fine-tuning quality is decided overwhelmingly by data quality, and a few hundred excellent examples beat tens of thousands of sloppy ones.

#Fine-Tuning#LLMs#AI Engineering#Data Engineering
Pratik Dhanave · ·5 min read

RAG vs Fine-Tuning vs Long-Context

The most common architecture mistake in applied AI is reaching for fine-tuning to fix a knowledge problem — so the single most useful rule here is that RAG is for knowledge and fine-tuning is for behavior, and long-context is a convenience, not a strategy.

The most common architecture mistake is reaching for fine-tuning to fix a knowledge problem — so the key rule: RAG is for knowledge, fine-tuning is for behavior, and long-context is a convenience, not a strategy.

#AI Architecture#RAG#Fine-Tuning#AI Engineering#Software Architecture#LLMs
Pratik Dhanave · ·5 min read

RAG, Fine-Tuning, and Self-Hosting Trade-offs

Some of the biggest cost decisions are architectural — whether to feed knowledge through retrieval or bake it into a model, whether to prompt a big model or fine-tune a small one, and whether to rent tokens or run your own — and each trade turns on your volume and your task.

Some of the biggest cost decisions are architectural — retrieval versus long context, prompting a big model versus fine-tuning a small one, and renting tokens versus self-hosting — each turning on your volume.

#AI Cost Optimization#AI Engineering#RAG#Fine-Tuning#LLMs#FinOps#Prompt Engineering
Pratik Dhanave · ·6 min read

QLoRA and Quantized Fine-Tuning

LoRA shrank the trainable parameters, but you still had to hold the full base model in memory to train against it — and for a large model that alone needs serious hardware. QLoRA closes the gap: quantize the frozen base model to 4-bit, train LoRA adapters on top, and fine-tune a large model on a single consumer GPU with almost no quality loss. It's what truly democratized fine-tuning.

LoRA shrank the trainable parameters, but you still had to hold the full base model in memory. QLoRA closes the gap: quantize the frozen base to 4-bit, train LoRA adapters on top, and fine-tune a large model on a single consumer GPU with almost no quality loss.

#Fine-Tuning#LLMs#AI Engineering#Performance
Pratik Dhanave · ·6 min read

Parameter-Efficient Fine-Tuning: LoRA

Full fine-tuning updates every weight in a model — billions of numbers — which needs enormous memory and produces a full-size copy per task. LoRA sidesteps all of it with one insight: the change a model needs for a task is "low-rank," so you can train a tiny pair of matrices instead of the whole model. It's the technique that put fine-tuning within reach of anyone with a single GPU.

Full fine-tuning updates every weight — billions of numbers — needing enormous memory. LoRA sidesteps it with one insight: the change a model needs for a task is low-rank, so you train a tiny pair of matrices instead of the whole model.

#Fine-Tuning#LLMs#AI Engineering#Performance
Pratik Dhanave · ·6 min read

The Fine-Tuning Spectrum

"Fine-tuning" is not one thing — it's a family of techniques that range from cheaply nudging a model's output format to expensively rebuilding its knowledge base. Confusing them leads to using a sledgehammer for a thumbtack. Knowing where your task sits on the spectrum tells you which technique, how much data, and how much compute you actually need.

'Fine-tuning' is not one thing — it's a family from cheaply nudging output format to expensively rebuilding a model's knowledge. Knowing where your task sits on the spectrum tells you which technique, how much data, and how much compute you actually need.

#Fine-Tuning#LLMs#AI Engineering#MLOps
Pratik Dhanave · ·6 min read

What Fine-Tuning Is and When to Use It

Fine-tuning is the most misunderstood tool in the LLM toolkit. Reach for it to teach a model new facts and you'll waste weeks and get worse results than a day of RAG. Reach for it to change how a model behaves — its format, tone, or a narrow skill — and nothing else comes close. The whole discipline starts with knowing which problem you actually have.

Fine-tuning is the most misunderstood tool in the LLM toolkit. Reach for it to teach a model facts and you'll waste weeks; reach for it to change how a model behaves — format, tone, a narrow skill — and nothing else comes close. The discipline starts with knowing which problem you have.

#Fine-Tuning#LLMs#AI Engineering#MLOps
Pratik Dhanave · ·5 min read

Building the System: Compose Before You Train

Modern production AI is rarely "a model" — it is a foundation model wrapped in retrieval, context engineering, tools, and guardrails — and the biggest architectural mistake is reaching for fine-tuning before exhausting the cheaper, more reversible options.

Production AI is rarely a model — it's a composed system, and the biggest mistake is fine-tuning before exhausting cheaper, reversible options. Phase 3: compose before you train.

#AI in Production#AI Engineering#AI Agents#RAG#MLOps#AI Governance#Fine-Tuning

All posts on this site are written by Pratik Dhanave, an Agentic AI Architect with 7+ years building production distributed systems, multi-agent AI platforms, and cloud-native infrastructure. About the author → Each article includes working code, architecture diagrams, and references to the specific frameworks and standards discussed. Browse all posts or explore related topics using the tag cloud above.