# #fine-tuning — MDRSS hashtag feed

> Public MDRSS cards tagged #fine-tuning.
> Canonical feed: https://mdrss.com/feeds/fine-tuning

## Cards (25)

### [Vision-Language SFT](https://mdrss.com/llm-engineering/training-and-fine-tuning/901378/901378.md)

This skill assumes finetuning-method-selection already routed here: the data shape is image+text demonstrations, not preference pairs or a verifiable reward signal, and the base is a vision-language model rather than a text-only one. lora-qlora-recipes covers the text-only Lo. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Trace To Training Data](https://mdrss.com/llm-engineering/training-and-fine-tuning/901376/901376.md)

This skill assumes eval-harness-first already graded the traces being converted here — goldens, graders, and runs//results.json all exist before conversion starts. This is the flywheel edge that skill names in its own flow: "the same labeled traces become the training set." C. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Preference Optimization](https://mdrss.com/llm-engineering/training-and-fine-tuning/901373/901373.md)

This skill assumes finetuning-method-selection already routed here because the data shape is preference pairs or unpaired thumbs-up/down feedback, not demonstrations (that's lora-qlora-recipes) or a verifiable reward signal (that's grpo-rlvr-training). What follows is metho. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [GRPO & RLVR Training](https://mdrss.com/llm-engineering/training-and-fine-tuning/901368/901368.md)

This skill assumes finetuning-method-selection already routed here because the target behavior has a verifiable pass/fail signal — not demonstrations (lora-qlora-recipes) or preference pairs (preference-optimization). What follows is when RL is the right tool, the reference. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Fine-Tuning Method Selection](https://mdrss.com/llm-engineering/training-and-fine-tuning/901366/901366.md)

This is the router skill for the fine-tuning lifecycle: it decides whether fine-tuning is the right tool at all, and if so, which method and which base-model size class. Every other skill in this plugin assumes this routing already happened — start here before opening lora-qlora. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Judge Calibration Protocol](https://mdrss.com/llm-engineering/training-and-fine-tuning/901365/901365.md)

The full procedure behind SKILL.md's "Judge Calibration Is a Prerequisite" section. Any grader routed to an LLM-judge follows this before its verdicts count toward a pass rate or a checkpoint promotion decision. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Checkpoint Promotion](https://mdrss.com/llm-engineering/training-and-fine-tuning/901358/901358.md)

The Phase 5 gate for the whole plugin: a checkpoint that trains cleanly and beats its task metric still doesn't ship without clearing all four stages below. eval-harness-first built the suite re-run here — this skill is where that suite's baseline decides something. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Fine-tune for: $ARGUMENTS](https://mdrss.com/llm-engineering/training-and-fine-tuning/901357/901357.md)

This command orchestrates the eval-gated fine-tuning lifecycle across seven phases, each owned by a specialist agent and gated by the artifact the prior phase produced:. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning training engineer](https://mdrss.com/llm-engineering/training-and-fine-tuning/901356/901356.md)

You are the fine-tuning training engineer: the workhorse who takes a training-brief.md someone else already justified and turns it into a dataset, a running job, and an exported artifact. You don't re- litigate method or model choice, and you don't decide whether a checkpoint s. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning eval engineer](https://mdrss.com/llm-engineering/training-and-fine-tuning/901355/901355.md)

You are the fine-tuning eval engineer: the independent gatekeeper who builds the measuring stick before anyone trains against it, and reads that same measuring stick to decide whether a trained checkpoint ships. You own the two phases that bound the lifecycle — Phase 0 before a t. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning architect](https://mdrss.com/llm-engineering/training-and-fine-tuning/901354/901354.md)

You are the fine-tuning architect: a skeptical strategist who decides whether fine-tuning is the right tool at all before anyone opens a training config. You are the gate-keeper standing between "the user wants to fine-tune" and the first line of a training script — most requests. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [SAM3-LoRA: Efficient Fine-Tuning with Low-Rank Adaptation](https://mdrss.com/llm-engineering/training-and-fine-tuning/901032/901032.md)

Quick Start • Architecture • Training • Validation • Inference • Examples • Configuration • Troubleshooting. Use it to ground design choices in named patterns, trade-offs and examples.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face](https://mdrss.com/llm-engineering/models-and-training/2517/2517.md)

Kindle | Paperback | PDF  Leanpub  | PDF  Gumroad  You can easily load the notebooks directly from GitHub using Colab and run them using a GPU provided by Google. You need to be logged in a Google Account of your own.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [SimpleTuner](https://mdrss.com/llm-engineering/models-and-training/2495/2495.md)

SimpleTuner is geared towards simplicity, with a focus on making the code easily understood. This codebase serves as a shared academic exercise, and contributions are welcome.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Welcome to RAGatouille](https://mdrss.com/learning/culture-and-creative/2320/2320.md)

Easily use and train state of the art retrieval methods in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Classification: learning/culture-and-creative · Feed: learning · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [BioBERT](https://mdrss.com/platforms/data-platforms/2270/2270.md)

This repository provides the code for fine-tuning BioBERT, a biomedical language representation model designed for biomedical text mining tasks such as biomedical named entity recognition, relation extraction, question answering, etc. Please refer to our paper BioBERT: a pre-trained biomedical language representation model for biomedical text mining for more details.

Classification: platforms/data-platforms · Feed: platforms · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Lit-LLaMA](https://mdrss.com/llm-engineering/serving-and-retrieval/2164/2164.md)

⚠️ Warning: Not Actively Maintained This repository is no longer actively maintained. For a more up-to-date alternative, please visit the LitGPT project: https://github.com/Lightning-AI/litgpt , which serves as the successor to this repository.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Ellora: Enhancing LLMs with LoRA](https://mdrss.com/llm-engineering/models-and-training/1965/1965.md)

The LLM ecosystem has amazing infrastructure (LoRAX, PEFT, vLLM), but lacks standardized, high-quality capability adapters. Problem: Base models limited to 32K context, need 2M tokens for large repositories Solution: Progressive curriculum learning with vLLM + Unsloth hybrid approach Key Innovation: Hybrid optimization combining vLLM's inference speed with Unsloth's training efficiency - achieving 61x context extension with minimal compute!

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [LLM Finetuning Toolkit](https://mdrss.com/llm-engineering/models-and-training/1963/1963.md)

LLM Finetuning toolkit is a config-based CLI tool for launching a series of LLM fine-tuning experiments on your data and gathering their results. From one single yaml config file, control all elements of a typical experimentation pipeline - prompts, open-source LLMs, optimization strategy and LLM testing.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [stable-audio-tools](https://mdrss.com/software-craft/developer-tooling/1927/1927.md)

Training and inference code for audio generation models Requires PyTorch 2.5 or later for Flash Attention and Flex Attention support. Development for the repo is done in Python 3.10.

Classification: software-craft/developer-tooling · Feed: software-craft · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms](https://mdrss.com/learning/culture-and-creative/1763/1763.md)

         NotaGen is a symbolic music generation model that explores the potential of producing high-quality classical sheet music. Inspired by the success of Large Language Models (LLMs), NotaGen adopts a three-stage training paradigm: Check our demo page and enjoy music composed by NotaGen!

Classification: learning/culture-and-creative · Feed: learning · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [XTuring](https://mdrss.com/llm-engineering/models-and-training/1740/1740.md)

Fine‑tune, evaluate, and run private, personalized LLMs xTuring makes it simple, fast, and cost‑efficient to fine‑tune open‑source LLMs (e.g., GPT‑OSS, LLaMA/LLaMA 2, Qwen3, MiniMax M2, GPT‑J, GPT‑2, DistilGPT‑2, Mamba) on your own data — locally or in your private cloud. Why xTuring: Run a small, CPU‑friendly example first: Want bigger models and reasoning controls?

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Peft](https://mdrss.com/llm-engineering/models-and-training/1168/1168.md)

🤗 PEFT State-of-the-art Parameter-Efficient Fine-Tuning (PEFT) methods Fine-tuning large pretrained models is often prohibitively costly due to their scale. Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of large pretrained models to various downstream applications by only fine-tuning a small number of (extra) model parameters instead of all the model's parameters.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [LLM Course](https://mdrss.com/llm-engineering/serving-and-retrieval/1089/1089.md)

𝕏 Follow me on X • 🤗 Hugging Face • 💻 Blog • 📙 LLM Engineer's Handbook The LLM course is divided into three parts: 1. 🧩 LLM Fundamentals is optional and covers fundamental knowledge about mathematics, Python, and neural networks.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Get started](https://mdrss.com/llm-engineering/serving-and-retrieval/1049/1049.md)

Unsloth Studio lets you run and train models locally. Features • News • Quickstart • Notebooks • Documentation Unsloth Studio (Beta) lets you run and train text, audio, embedding, vision models on Windows, Linux and macOS.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1