Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/smol-course
Library/smol-courseForked

huggingface/smol-course

smol-course

A course on aligning smol models.

View on GitHub↗Upstream huggingface/smol-course↗

Builder

HuggingFace

HuggingFace

huggingface • ai-lab

Stars

6,647

Using upstream star count

Forks

2,285

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Nov 25, 2024

Project creation date

README Summary

This is a practical course on aligning language models for your specific use case. It's a handy way to get started with aligning language models, because everything runs on most local machines. There are minimal GPU requirements and no paid services. The course is built around the [SmolLM3](https://huggingface.co/blog/smollm3) and [SmolVLM2](https://huggingface.co/blog/smolvlm2) models, but the skills you'll learn can be applied to larger models or other small LLMs/VLMs as well.

Community Evaluation

Loading…

AI Dev Skills

Unmapped

AI Alignment TechniquesConstitutional AIDirect Preference OptimizationEthical AI DevelopmentHuman Preference LearningModel Fine-tuningModel SafetyReinforcement Learning from Human FeedbackSmall Language Model Training

Tags

AI Alignment TechniquesConstitutional AIDirect Preference OptimizationEthical AI DevelopmentHuman Preference LearningModel Fine-tuningModel SafetyReinforcement Learning from Human FeedbackSmall Language Model TrainingAI SafetyBenchmarkingCourseDPOData ScienceEvalsForkedHuggingFaceLarge Language ModelsMachine LearningMultimodal AIPyTorchPythonReinforcement LearningSynthetic DataTransformers

Taxonomy

AI Trends

Small Language ModelsAI SafetyAI AlignmentResponsible AIEducational AI

category

Foundation ModelsModel TrainingEvals & BenchmarkingLearning ResourcesSecurity & SafetyData Science & Analytics

Deployment Context

Self-hostedCloud API

Industries

EducationAI ResearchDeveloper Tools

Modalities

Text

Skill Areas

Small Language Model TrainingAI Alignment TechniquesModel Fine-tuningHuman Preference LearningReinforcement Learning from Human FeedbackConstitutional AIDirect Preference OptimizationModel SafetyEthical AI Development

tag

AI SafetyBenchmarkingCourseDPOData ScienceEvalsForkedHuggingFaceLarge Language ModelsMachine LearningMultimodal AIPyTorchPythonReinforcement LearningSynthetic DataTransformers

Use Cases

AI Safety EducationModel Alignment TrainingSmall Model OptimizationResponsible AI DevelopmentAcademic Research Training

Recent Activity

Updated 3 months ago

7 Days

0

30 Days

0

90 Days

0

Eliminate duplicate text chunk (#290)

Muscle-Oliver • Feb 6, 2026

b38ea28

Quality

research
Quality
medium
Maturity
research

Categories

Evals & BenchmarkingPrimaryLearning ResourcesSecurity & SafetyData Science & AnalyticsFoundation ModelsModel TrainingSafety & AlignmentMultimodal AIOther AI / ML

PM Skills

Safety & AlignmentUser ExperienceData & Evaluation

Languages

Jupyter Notebook100.0%

Timeline

Project created
Nov 25, 2024
Forked
Mar 12, 2026
Your last push
3 months ago
Upstream last push
1 months ago
Tracked since
Feb 6, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…