---
id: "/model-training/page/5/"
title: "Model Training · page 5"
creator: null
creator_url: null
creator_x: null
url: "https://skillissue.dev/model-training/page/5/"
level: null
level_max: null
category: null
subcategory: null
region: null
license: null
license_scope: null
access: null
models: null
source_date: null
date_added: null
resource_kind: null
verification_basis: null
access_evidence: null
domain_top: null
domain_sub: null
last_verified: null
---

# Model Training

Study the data, algorithms and infrastructure used to change model weights.

- [Pretraining](/model-training/pretraining/index.md) (3)

- [Training Data](/model-training/training-data/index.md) (1)

- [Post Training Rl](/model-training/post-training-rl/index.md) (5)

- [Fine Tuning](/model-training/fine-tuning/index.md) (4)

- [Training Infrastructure](/model-training/training-infrastructure/index.md) (123)

[Beginner](/model-training/beginner/index.md) [Intermediate](/model-training/intermediate/index.md) [Advanced](/model-training/advanced/index.md) [Expert](/model-training/expert/index.md)

136 resources · page 5 of 5

- 

### [How to Scale Your Model (JAX scaling book)](/model-training/training-infrastructure/how-to-scale-your-model-jax-scaling-book/index.md)

Creator not supplied; see original source.

How to Scale Your Model: free online book on TPU/GPU rooflines, transformer math, parallelism and serving for LLMs.

Expert · unknown · unknown resource · en 

- 

### [The Smol Training Playbook](/model-training/pretraining/hugging-face-the-smol-training-playbook/index.md)

by [Hugging Face (SmolLM team)](https://huggingfacetb-smol-training-playbook.hf.space/)

A training account that includes failed experiments and engineering decisions.

Expert · other · closed resource · en 

- 

### [The Ultra-Scale Playbook](/model-training/training-infrastructure/hugging-face-the-ultra-scale-playbook/index.md)

by [Hugging Face (nanotron)](https://nanotron-ultrascale-playbook.static.hf.space/index.html)

Understand how parallelism changes memory use and training throughput.

Expert · other · closed resource · en 

- 

### [The FineWeb Datasets](/model-training/training-data/huggingface-fineweb/index.md)

by [Guilherme Penedo and coauthors, Hugging Face](https://arxiv.org/abs/2406.17557)

Study how filtering and deduplication affect pretraining data.

Expert · other · open resource · en 

- 

### [PagedAttention / vLLM paper](/model-training/training-infrastructure/pagedattention-vllm-paper/index.md)

Creator not supplied; see original source.

arXiv paper (2023) introducing PagedAttention and the vLLM serving system for efficient KV-cache memory management.

Expert · unknown · unknown resource · en 

- 

### [SGLang docs](/model-training/training-infrastructure/sglang-docs/index.md)

Creator not supplied; see original source.

SGLang documentation: LLM serving framework with RadixAttention prefix caching and fast structured outputs.

Expert · unknown · unknown resource · en 

- 

### [How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance (Simon Boehm)](/model-training/training-infrastructure/simon-boehm-cuda-matmul-worklog/index.md)

Creator not supplied; see original source.

Simon Boehm's worklog optimising a CUDA matrix-multiplication kernel step by step towards cuBLAS performance.

Expert · unknown · unknown resource · en 

- 

### [verl (HybridFlow)](/model-training/post-training-rl/verl-project-verl/index.md)

by [verl project (originated at ByteDance Seed)](https://github.com/verl-project/verl)

Explore how an RL training framework coordinates generation and optimization.

Expert · CN · open resource · en 

[Previous page](/model-training/page/4/index.md) 

[Plain-text Markdown copy](/model-training/page/5/index.md)