{"data":{"slug":"rohan-paul-llm-finetuning-large-language-models","name":"LLM-FineTuning-Large-Language-Models","tagline":"LLM FineTuning","github_url":"https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models","owner":"rohan-paul","repo":"LLM-FineTuning-Large-Language-Models","owner_avatar_url":"https://avatars.githubusercontent.com/u/12703975?v=4","primary_language":"Jupyter Notebook","stars":577,"forks":136,"topics":["gpt-3","gpt3-turbo","large-language-models","llama2","llm","llm-finetuning","llm-inference","llm-serving","llm-training","mistral-7b","open-source-llm","pytorch"],"archived":false,"github_pushed_at":"2025-04-01T21:05:06+00:00","maintenance_label":"Dormant","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/rohan-paul-llm-finetuning-large-language-models","markdown_url":"https://www.graphcanon.com/tools/rohan-paul-llm-finetuning-large-language-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rohan-paul-llm-finetuning-large-language-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rohan-paul-llm-finetuning-large-language-models","description":"LLM (Large Language Model) FineTuning","homepage_url":null,"license":null,"open_issues":2,"watchers":8,"ai_summary":"A Jupyter Notebook repository focused on fine-tuning large language models including GPT-3, GPT3-Turbo, LLaMA2, and Mistral-7B using Pytorch.","readme_excerpt":"# LLM (Large Language Models) FineTuning Projects and notes on common practical techniques\n\n# [Find me in Twitter](https://twitter.com/rohanpaul_ai)\n\n## [📚 I write daily for my 112K+ readers on actionable AI developments. Get a 1300+ page Python book as soon as you subscribing (its FREE) ↓↓)](https://www.rohan-paul.com/s/daily-ai-newsletter/archive?sort=new)\n\n[logo]: https://github.com/rohan-paul/rohan-paul/blob/master/assets/newsletter_rohan.png\n\n[![Rohan's Newsletter][logo]](https://www.rohan-paul.com/) &nbsp;\n\n\n\n### Fine-tuning LLM (and YouTube Video Explanations)\n\n| Notebook | 🟠 **YouTube Video**|\n| -------- | ---------------------- |\n| [Finetune Llama-3-8B with unsloth 4bit quantized with ORPO](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/Llama_3_Finetuning_ORPO_with_Unsloth.ipynb) | [![Youtube Link][logo]](https://www.youtube.com/watch?v=6ikUpJcDrPs&list=PLxqBkZuBynVTzqUQCQFgetR97y1X_1uCI&index=31) |\n| [Llama-3 Finetuning on custom dataset with unsloth](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/Llama-3_Finetuning_on_custom_dataset_with_unsloth.ipynb) | [![Youtube Link][logo]](https://www.youtube.com/watch?v=AmVEGPS9JIg&list=PLxqBkZuBynVTzqUQCQFgetR97y1X_1uCI&index=25) |\n| [CodeLLaMA-34B - Conversational Agent ](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/CodeLLaMA_34B_Conversation_with_Streamlit.py) | [![Youtube Link][logo]](https://www.youtube.com/watch?v=815NpXvniIg&list=PLxqBkZuBynVTzqUQCQFgetR97y1X_1uCI&index=16&ab_channel=Rohan-Paul-AI) |\n| [Inference Yarn-Llama-2-13b-128k with KV Cache to answer quiz on very long textbook](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/Inference_Yarn-Llama-2-13b-128k_Github.ipynb) | [![Youtube Link][logo]](https://www.youtube.com/watch?v=RYTOQERqVsg&list=PLxqBkZuBynVTzqUQCQFgetR97y1X_1uCI&index=14&ab_channel=Rohan-Paul-AI)|\n| [Mistral 7B FineTuning with_PEFT and QLORA](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/Mistral_FineTuning_with_PEFT_and_QLORA.ipynb) | [![Youtube Link][logo]](https://www.youtube.com/watch?v=6DGYj1EEWOw&list=PLxqBkZuBynVTzqUQCQFgetR97y1X_1uCI&index=13&ab_channel=Rohan-Paul-AI)|\n| [Falcon finetuning on openassistant-guanaco](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/Falcon-7B_FineTuning_with_PEFT_and_QLORA.ipynb) | [![Youtube Link][logo]](https://www.youtube.com/watch?v=fEzuBFi35J4&list=PLxqBkZuBynVTzqUQCQFgetR97y1X_1uCI&index=11&ab_channel=Rohan-Paul-AI)|\n| [Fine Tuning Phi 1_5 with PEFT and QLoRA](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/FineTuning_phi-1_5_with_PRFT_LoRA.ipynb) | [![Youtube Link][logo]](https://www.youtube.com/watch?v=J0RbOtLrJhQ&list=PLxqBkZuBynVTzqUQCQFgetR97y1X_1uCI&index=10&ab_channel=Rohan-Paul-AI)|\n| [Web scraping with Large Language Models (LLM)-AnthropicAI + LangChainAI](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/Web%20scraping%20with%20Large%20Language%20Models%20(LLM)-AnthropicAI%20%2B%20LangChainAI.ipynb) | [![Youtube Link][logo]](https://www.youtube.com/watch?v=QAY82UvrsHg&list=PLxqBkZuBynVTiTEvP6-GYf35yA6OqIN7Y&index=2&ab_channel=Rohan-Paul-AI)|\n\n\n---------------------------\n\n### Fine-tuning LLM\n\n| Notebook | Colab |\n| -------- | ------------- |\n| 📌 [Gemma_2b_finetuning_ORPO_full_precision](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/gemma-2b_ORPO_FineTuning_full_precision/v2_Colab_Gemma_2b_orpo.ipynb)|<a href=\"https://colab.research.google.com/github/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/gemma-2b_ORPO_FineTuning_full_precision/Gemma_2b_orpo_full_precision_Colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n| 📌 [Jamba_Finetuning_Colab-Pro](https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models/blob/main/tinyllama_fine-tuning_Ta","github_created_at":"2023-10-22T22:04:09+00:00","created_at":"2026-07-11T11:45:05.415234+00:00","updated_at":"2026-08-25T06:01:58.166047+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"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":"gpt-3","name":"gpt-3"},{"slug":"gpt3-turbo","name":"gpt3-turbo"},{"slug":"llama2","name":"llama2"},{"slug":"mistral-7b","name":"mistral-7b"},{"slug":"open-source-llm","name":"open-source-llm"},{"slug":"pytorch","name":"pytorch"}],"trust":{"provenance":{"is_fork":false,"github_id":708552127,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-25T06:01:57.436Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":510,"last_release_at":null,"stars_delta_30d":1,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:45:06.630Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-25T06:01:57.890Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-08-25T06:01:57.890Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["When you specifically need to work with GPT-3, GPT3-Turbo, LLaMA2, or Mistral-7B models within a Jupyter Notebook environment for fine-tuning tasks.","If your project requires the flexibility and precision of Pytorch for adjusting pre-trained language models."],"when_not_to_use":["Do not use this repository if you are looking to work with frameworks other than Pytorch, as it is specifically tied to Pytorch implementations.","Avoid choosing this tool if you do not need model finetuning capabilities and instead require only inference or serving services from your language models."],"source":"enrich:decision_facts","observed_at":"2026-07-16T20:32:37.073Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Adopt for","value":"LLM-FineTuning-Large-Language-Models is a Jupyter Notebook repository focused on fine-tuning large language models including GPT-3, GPT3-Turbo, LLaMA2, and Mistral-7B using Pytorch."},{"label":"License detail","value":"The license information for LLM-FineTuning-Large-Language-Models was not explicitly provided in the repository details given."}]}}