{"data":{"slug":"skalskip-vlms-zero-to-hero","name":"vlms-zero-to-hero","tagline":"Journey from NLP fundamentals to Vision-Language Models","github_url":"https://github.com/SkalskiP/vlms-zero-to-hero","owner":"SkalskiP","repo":"vlms-zero-to-hero","owner_avatar_url":"https://avatars.githubusercontent.com/u/26109316?v=4","primary_language":"Jupyter Notebook","stars":1180,"forks":105,"topics":["bert-model","clip","computer-vision","embeddings","gpt","gpt-2","lora","natural-language-processing","seq2seq","vision-language-model","word2vec"],"archived":false,"github_pushed_at":"2025-01-23T11:23:09+00:00","maintenance_label":"Dormant","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/skalskip-vlms-zero-to-hero","markdown_url":"https://www.graphcanon.com/tools/skalskip-vlms-zero-to-hero.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/skalskip-vlms-zero-to-hero","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=skalskip-vlms-zero-to-hero","description":"This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.","homepage_url":"https://www.youtube.com/@SkalskiP","license":"Apache-2.0","open_issues":2,"watchers":47,"ai_summary":"A series covering foundations of Natural Language Processing and Computer Vision leading to advanced Vision-Language models, utilizing frameworks like BERT, CLIP, GPT, and more.","readme_excerpt":"<div align=\"center\">\n\n  <h1 align=\"center\">VLMs zero-to-hero</h1>\n\n  <p>coming: january 2025...</p>\n\n</div>\n\n# hello\n\nWelcome to VLMs Zero to Hero! This series will take you on a journey from the \nfundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.\n\n# tutorials\n\n|                                                                                                                                 **notebook**                                                                                                                                  |                                                                                              **open in colab**                                                                                              | **video** |                **paper**                |\n|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------:|:---------------------------------------:|\n| 01.01. [Word2Veq: Distributed Representations of Words and Phrases and their Compositionality](https://github.com/SkalskiP/vlms-zero-to-hero/blob/master/01_natural_language_processing_fundamentals/01_01_word2vec_with_sub_sampling_and_negative_sampling_in_pytorch.ipynb) | [link](https://colab.research.google.com/github/SkalskiP/vlms-zero-to-hero/blob/master/01_natural_language_processing_fundamentals/01_01_word2vec_with_sub_sampling_and_negative_sampling_in_pytorch.ipynb) |   soon    | [link](https://arxiv.org/abs/1310.4546) |\n\n# roadmap\n\n## natural language processing (NLP) fundamentals\n\n- Word2Veq: [Efficient Estimation of Word Representations in Vector Space](https://arxiv.org/pdf/1301.3781) (2013) and [Distributed Representations of Words and Phrases and their Compositionality](https://arxiv.org/pdf/1310.4546) (2013) \n- Seq2Seq: [Sequence to Sequence Learning with Neural Networks](https://arxiv.org/pdf/1409.3215) (2014)\n- [Attention Is All You Need](https://arxiv.org/pdf/1706.03762) (2017)\n- BERT: [Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/pdf/1810.04805) (2018)\n- GPT: [Improving Language Understanding by Generative Pre-Training](https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf) (2018)\n\n## computer vision (CV) fundamentals\n\n- AlexNet: [ImageNet Classification with Deep Convolutional Neural Networks](https://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf) (2012)\n- VGG: [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/pdf/1409.1556) (2014)\n- ResNet: [Deep Residual Learning for Image Recognition](https://arxiv.org/pdf/1512.03385) (2015)\n\n## early vision-language models\n\n- [Show and Tell: A Neural Image Caption Generator](https://arxiv.org/pdf/1411.4555) (2014) and [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://arxiv.org/pdf/1502.03044) (2015)\n- [A Picture is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/pdf/2010.11929) (2020)\n- CLIP: [Learning Transferable Visual Models from Natural Language Supervision](https://arxiv.org/pdf/2103.00020) (2021)\n\n## scale and efficiency\n\n- [Scaling Laws for Neural Language Models](https://arxiv.org/pdf/2001.08361) (2020)\n- LoRA: [Low-Rank Adaptation of Large Language Models](https://arxiv.org/pdf/2106.09685) (2021)\n- QLoRA: [Efficient Fine-tuning of Quantized LLMs](https://arxiv.org/pdf/2305.14314) (2023)\n\n## modern vision-language models\n\n- Flamingo: [A Visual Language Model for Few-Shot Learning](h","github_created_at":"2024-12-20T08:02:26+00:00","created_at":"2026-07-11T11:31:24.700459+00:00","updated_at":"2026-09-20T06:16:15.271267+00:00","categories":[{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"bert-model","name":"bert-model"},{"slug":"clip","name":"clip"},{"slug":"computer-vision","name":"computer-vision"},{"slug":"embeddings","name":"embeddings"},{"slug":"gpt","name":"gpt"},{"slug":"gpt-2","name":"gpt-2"},{"slug":"lora","name":"lora"},{"slug":"natural-language-processing","name":"natural language processing"}],"trust":{"provenance":{"is_fork":false,"github_id":906122697,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:16:12.560Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":604,"last_release_at":null,"stars_delta_30d":1,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:31:25.960Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:16:14.583Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-09-20T06:16:14.583Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T06:16:14.583Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free to use with no hidden costs due to its open-source nature."},"requirements":{"notes":["Requires a basic understanding of Python. Access to Jupyter Notebook is necessary."],"requires_docker":false},"constraints":{"pricing_model":"freemium","requires_docker":false},"when_to_use":["Use 'vlms-zero-to-hero' when you want an in-depth, step-by-step introduction that ranges from foundational NLP and CV concepts up to advanced Vision-Language models.","Choose this tool if you are interested in leveraging specific frameworks such as BERT, CLIP, and GPT-2 for building your own vision-language model.","This is ideal for learners who prefer interactive Jupyter Notebook tutorials with practical exercises and clear explanations."],"when_not_to_use":["Avoid 'vlms-zero-to-hero' if you have an advanced background in both NLP and Vision-Language Models and are looking for immediate hands-on experience rather than theoretical depth.","Do not use this tool if you require a quick solution or implementation of vision-language models, as it emphasizes comprehensive learning and conceptual understanding."],"source":"enrich:decision_facts","observed_at":"2026-07-12T10:46:32.478Z"},"constraint_facets":{"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - Free to use with no hidden costs due to its open-source nature."},{"label":"Requirements","value":"Requires a basic understanding of Python. Access to Jupyter Notebook is necessary."},{"label":"Adopt for","value":"A comprehensive guide for those seeking a deep understanding of NLP and CV leading to advanced Vision-Language models."},{"label":"License detail","value":"The 'vlms-zero-to-hero' repository is licensed under Apache-2.0 which allows for free use, modification and distribution."}]}}