# iusztinpaul/hands-on-llms

🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴

Repository: https://github.com/iusztinpaul/hands-on-llms
Canonical: https://ross.abutalabs.com/products/hands-on-llms
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: bytewax, comet-ml, huggingface, mlops, qdrant, transformers, beam, langchain, generative-ai, llms, 3-pipeline-design, aws, cicd, fine-tuning, llmops, qlora, streaming, docker
Archived: true
Last push: 2024-12-09T14:55:28+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 83
- inputs: {"age_days": 1162, "days_push": 632, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3422, forks 553 (observed 2026-08-28T04:08:03.836735+00:00)

## What it is
A free open-source course teaching LLMs, LLMOps, and vector databases by building a real-time financial advisor LLM system with training, streaming, and inference pipelines. It includes source code, video lectures, and reading materials, now superseded by the LLM Twin course.

## Use cases
- learn llmops hands-on
- fine-tune an llm with qlora
- build a rag system with qdrant
- learn streaming pipelines with bytewax
- deploy llm training on serverless gpus
- free llm course with code

## When to choose
- you want project-based learning covering the full LLM lifecycle
- you need practical exposure to Qdrant, Comet ML, Beam, and AWS
- you want to learn fine-tuning and real-time inference together

## When to avoid
- you want the latest maintained curriculum - use the LLM Twin course instead
- you need production-ready software rather than educational material
- you lack a CUDA GPU and don't want cloud costs

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-training, rag, machine-learning, etl, streaming
- domain: large-language-models, machine-learning, education, fintech
- platform: python, cloud
- tags: llmops, qlora, fine-tuning, vector-database, qdrant, langchain, bytewax, free-course, docker

## Member repositories
- iusztinpaul/hands-on-llms (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:03.836735+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:38:08.758105+00:00, confidence not recorded.
  - readme: https://github.com/iusztinpaul/hands-on-llms (fetched 2026-08-28T04:08:03.836735+00:00, sha 719314c10d58)
- Data as of 2026-08-30T08:39:29.467469+00:00.