| Bonus Resources.txt | 102.4 B | ||
| Get Bonus Downloads Here.url | 204.8 B | ||
| ~Get Your Files Here ! | |||
| 1 - Text as data | |||
| 1. Welcome and what this course is for.mp4 | 9.7 MB | ||
| 1. Welcome and what this course is for_en-US.srt | 3.5 KB | ||
| 2. 01-text-as-data-01-why-text-is-hard.en.pdf | 63 KB | ||
| 2. Why text is hard, and the NLP task landscape.mp4 | 25.5 MB | ||
| 2. Why text is hard, and the NLP task landscape_en-US.srt | 8 KB | ||
| 3. 01-text-as-data-02-tokens-bow-tfidf.en.pdf | 92.3 KB | ||
| 3. Tokens, bag of words, TF-IDF.mp4 | 24.5 MB | ||
| 3. Tokens, bag of words, TF-IDF_en-US.srt | 8.3 KB | ||
| 4. 01-text-as-data-03-lab-sentiment-baseline.en.pdf | 81.4 KB | ||
| 4. Lab a sentiment baseline on real reviews.mp4 | 22.4 MB | ||
| 4. Lab a sentiment baseline on real reviews_en-US.srt | 8.1 KB | ||
| 4. solutions-01-sentiment-baseline-solution.ipynb.bin | 33.5 KB | ||
| 4. starter-01-sentiment-baseline.ipynb.bin | 29.3 KB | ||
| README.md | 1.3 KB | ||
| scikit_learn_data | |||
| 20news-bydate_py3.pkz | 14.6 MB | ||
| uci | |||
| __MACOSX | |||
| _sentiment labelled sentences | 204.8 B | ||
| sentiment labelled sentences | |||
| _.DS_Store | 204.8 B | ||
| _imdb_labelled.txt | 204.8 B | ||
| _readme.txt | 204.8 B | ||
| sentiment labelled sentences | |||
| 2 - Embeddings | |||
| 3 - Attention and the Transformer | |||
| 10. 03-attention-transformer-03-the-full-block.en.pdf | 98.1 KB | ||
| 10. The full block multi-head, feed-forward, residuals, positions.mp4 | 26 MB | ||
| 10. The full block multi-head, feed-forward, residuals, positions_en-US.srt | 8.6 KB | ||
| 11. 03-attention-transformer-04-encoder-decoder-families.en.pdf | 57.4 KB | ||
| 11. Encoder, decoder, or both BERT, GPT and T5.mp4 | 29.9 MB | ||
| 11. Encoder, decoder, or both BERT, GPT and T5_en-US.srt | 8.8 KB | ||
| 4 - How LLMs are made | |||
| 12. 04-how-llms-are-made-01-pretraining.en.pdf | 74.9 KB | ||
| 12. Pretraining objective, data, and scale.mp4 | 25.9 MB | ||
| 12. Pretraining objective, data, and scale_en-US.srt | 8.5 KB | ||
| 13. 04-how-llms-are-made-02-gpt-lineage.en.pdf | 62.8 KB | ||
| 13. The GPT lineage as a series of bets.mp4 | 27.8 MB | ||
| 13. The GPT lineage as a series of bets_en-US.srt | 8 KB | ||
| 14. 04-how-llms-are-made-03-instruction-tuning-rlhf.en.pdf | 89.2 KB | ||
| 14. Instruction tuning and RLHF.mp4 | 28.5 MB | ||
| 14. Instruction tuning and RLHF_en-US.srt | 9.1 KB | ||
| 15. 04-how-llms-are-made-04-open-model-world.en.pdf | 65 KB | ||
| 15. The open-model world.mp4 | 29.8 MB | ||
| 15. The open-model world_en-US.srt | 8.7 KB | ||
| 5 - Using LLMs well | |||
| 16. 05-using-llms-well-01-sampling.en.pdf | 70.8 KB | ||
| 16. The open-model world.mp4 | 22.5 MB | ||
| 16. The open-model world_en-US.srt | 8 KB | ||
| 17. 05-using-llms-well-02-prompting-in-production.en.pdf | 66 KB | ||
| 17. Prompting that survives contact with production.mp4 | 26.3 MB | ||
| 17. Prompting that survives contact with production_en-US.srt | 8.1 KB | ||
| 18. 05-using-llms-well-03-structured-output-tools.en.pdf | 70.7 KB | ||
| 18. Structured output and tool calling.mp4 | 25.3 MB | ||
| 18. Structured output and tool calling_en-US.srt | 8.4 KB | ||
| 19. 05-using-llms-well-04-context-cost-latency.en.pdf | 72 KB | ||
| 19. Context windows, cost, and latency budgets.mp4 | 24 MB | ||
| 19. Context windows, cost, and latency budgets_en-US.srt | 8.5 KB | ||
| 6 - RAG | |||
| 20. 06-rag-01-why-rag.en.pdf | 54.6 KB | ||
| 20. Why RAG knowledge, freshness, and grounding.mp4 | 26.4 MB | ||
| 20. Why RAG knowledge, freshness, and grounding_en-US.srt | 7.8 KB | ||
| 21. 06-rag-02-chunking-and-retrieval-quality.en.pdf | 64.5 KB | ||
| 21. Chunking, embedding, and retrieval quality.mp4 | 25.2 MB | ||
| 21. Chunking, embedding, and retrieval quality_en-US.srt | 8.2 KB | ||
| 22. 06-rag-03-lab-rag-over-documents.en.pdf | 60.2 KB | ||
| 22. Lab RAG over your own documents.mp4 | 24.9 MB | ||
| 22. Lab RAG over your own documents_en-US.srt | 7.9 KB | ||
| 22. solutions-06-rag-over-documents-solution.ipynb.bin | 52.5 KB | ||
| 22. starter-06-rag-over-documents.ipynb.bin | 48.1 KB | ||
| 7 - Fine-tuning | |||
| 23. 07-fine-tuning-01-when-to-fine-tune.en.pdf | 52.8 KB | ||
| 23. When to fine-tune, and the cheaper alternatives.mp4 | 37.5 MB | ||
| 23. When to fine-tune, and the cheaper alternatives_en-US.srt | 9.7 KB | ||
| 24. 07-fine-tuning-02-lora.en.pdf | 66.9 KB | ||
| 24. LoRA, the mechanism and the knobs.mp4 | 35.4 MB | ||
| 24. LoRA, the mechanism and the knobs_en-US.srt | 10.9 KB | ||
| 25. 07-fine-tuning-03-lab-lora-fine-tune.en.pdf | 67.3 KB | ||
| 25. Lab LoRA fine-tune a small model.mp4 | 35.4 MB | ||
| 25. Lab LoRA fine-tune a small model_en-US.srt | 9.4 KB | ||
| 25. solutions-07-lora-fine-tune-solution.ipynb.bin | 43.2 KB | ||
| 25. starter-07-lora-fine-tune.ipynb.bin | 33.4 KB | ||
| 8 - Evaluation and failure modes | |||
| 26. 08-evaluation-01-failure-modes.en.pdf | 61.8 KB | ||
| 26. Hallucination, sycophancy, and other systematic failures.mp4 | 36.1 MB | ||
| 26. Hallucination, sycophancy, and other systematic failures_en-US.srt | 11.3 KB | ||
| 27. 08-evaluation-02-evals.en.pdf | 59.7 KB | ||
| 27. Evals golden sets, LLM-as-judge, regression harnesses.mp4 | 44.5 MB | ||
| 27. Evals golden sets, LLM-as-judge, regression harnesses_en-US.srt | 12.3 KB | ||
| 28. 08-evaluation-03-safety-basics.en.pdf | 59 KB | ||
| 28. Safety-relevant behaviour injection and leakage basics.mp4 | 35.6 MB | ||
| 28. Safety-relevant behaviour injection and leakage basics_en-US.srt | 9.8 KB | ||
| 9 - Capstone | |||
| 29. 09-capstone-01-capstone-classical-vs-llm.en.pdf | 60 KB | ||
| 29. Capstone classical versus LLM on the same task, measured.mp4 | 37.2 MB | ||
| 29. Capstone classical versus LLM on the same task, measured_en-US.srt | 9.8 KB | ||
| 29. solutions-09-capstone-classical-vs-llm-solution.ipynb.bin | 49.2 KB | ||
| 29. starter-09-capstone-classical-vs-llm.ipynb.bin | 36.4 KB | ||
| 30. 09-capstone-02-keeping-current.en.pdf | 40.8 KB | ||
| 30. Where the field is going, and keeping current without drowning.mp4 | 43.5 MB | ||
| 30. Where the field is going, and keeping current without drowning_en-US.srt | 10.6 KB | ||
| 30. c2-next-steps.en.pdf | 29.8 KB | ||
| 8. 03-attention-transformer-01-problem-attention-solves.en.pdf | 67.2 KB | ||
| 8. The problem attention solves.mp4 | 17.3 MB | ||
| 8. The problem attention solves_en-US.srt | 6.4 KB | ||
| 9. 03-attention-transformer-02-self-attention-step-by-step.en.pdf | 85.1 KB | ||
| 9. Self-attention, step by step with shapes.mp4 | 19.6 MB | ||
| 9. Self-attention, step by step with shapes_en-US.srt | 7.1 KB | ||
| 5. 02-embeddings-01-counts-to-meaning.en.pdf | 72.2 KB | ||
| 5. From counts to meaning dense vectors.mp4 | 24.4 MB | ||
| 5. From counts to meaning dense vectors_en-US.srt | 7.7 KB | ||
| 6. 02-embeddings-02-word2vec-and-friends.en.pdf | 69.9 KB | ||
| 6. word2vec and friends, briefly.mp4 | 28.8 MB | ||
| 6. word2vec and friends, briefly_en-US.srt | 8.6 KB | ||
| 7. 02-embeddings-03-lab-search-clustering.en.pdf | 69.6 KB | ||
| 7. Lab embeddings for search and clustering.mp4 | 21.8 MB | ||
| 7. Lab embeddings for search and clustering_en-US.srt | 7.2 KB | ||
| 7. solutions-02-search-clustering-solution.ipynb.bin | 33.4 KB | ||
| 7. starter-02-search-clustering.ipynb.bin | 31.2 KB | ||
| DS_Store | 6 KB | ||
| amazon_cells_labelled.txt | 56.9 KB | ||
| imdb_labelled.txt | 83.3 KB | ||
| readme.txt | 1 KB | ||
| yelp_labelled.txt | 59.9 KB |
NLP to LLMs: Build the Understanding That Lasts
https://WebToolTip.com
Published 8/2026
Created by OfferLab Courses
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz, 2 Ch
Level: Intermediate | Genre: eLearning | Language: English + subtitle | Duration: 30 Lectures ( 2h 55m ) | Size: 859 MB
Attention traced by hand, LoRA written from scratch, RAG and evals measured. No GPU, no paid API, ever.
What you'll learn
⚡ Frame any text problem as a standard task type, and ship a TF-IDF baseline that earns its keep
⚡ Trace one attention head by hand, with real shapes, until the mechanism stops being a metaphor
⚡ Diagram a full transformer block from memory: multi-head, feed-forward, residuals, positions
⚡ Narrate the GPT lineage as a series of specific bets, and explain why chat models behave unlike base models
⚡ Control generation on purpose with temperature and top-p, and get reliable JSON and tool calls
⚡ Estimate and cut the cost of an LLM feature before you build it, using context and latency budgets
⚡ Build a RAG system and debug retrieval with recall checks rather than vibes
⚡ Run a real LoRA fine-tune on a laptop CPU, verify the gain, and defend the build decision with your own numbers
Requirements
❗ Comfortable Python (you can read a class and a loop)
❗ Some exposure to machine learning basics helps but is not required
❗ No GPU, no paid API key, no cloud account. Every lab runs on a laptop CPU
| torrent name | size | uploader | age | seed | leech |
|---|---|---|---|---|---|
| 2.7 GB | freecoursewb | 6 months | 1 | 0 | |
| 2.5 GB | freecoursewb | 8 months | 7 | 0 | |
| 1.6 GB | freecoursewb | 11 months | 1 | 1 | |
| 2 GB | freecoursewb | 1 year | 2 | 0 | |
| 849 MB | freecoursewb | 1 year | 2 | 0 |
All Comments