{"full_name":"meta-llama/llama-cookbook","owner":"meta-llama","name":"llama-cookbook","shard":"1","url":"https://github.com/meta-llama/llama-cookbook","description":"Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services  ","homepage":"https://www.llama.com","topics":["ai","finetuning","langchain","llama","llama2","llm","machine-learning","python","pytorch","vllm"],"tag_pages":["ai","langchain","llama","llm","machine-learning","python","pytorch","vllm"],"language":"Jupyter Notebook","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/153379578?v=4","created_at":"2023-07-17T07:33:48Z","pushed_at":"2026-05-19T18:42:31Z","metrics":{"stars":18594,"forks":2758,"watchers":195,"issues":452,"prs":613,"releases":4,"issues_open":24,"issues_closed":428,"prs_open":77,"prs_closed":130,"prs_merged":406,"discussions":0},"growth":{"day":{"stars":0,"forks":1,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[18589,18589,18590,18591,18594,18594,18594],"forks":[2756,2756,2757,2757,2757,2757,2758],"watchers":[null,195,195,195,195,195,195],"issues_open":[null,24,24,24,24,24,24],"prs_open":[null,76,76,76,76,76,77]},"boards":{},"same_owner":[{"full_name":"meta-llama/codellama","name":"codellama","shard":"1","boards":{}},{"full_name":"meta-llama/llama","name":"llama","shard":"1","boards":{"daily_watchers":69}}],"issues":[{"number":810,"title":"Reproduction issue of task GSM8K with Llama3.2-1B-Instruct","comments":7,"created_at":"2024-12-05T05:38:15Z"},{"number":949,"title":"CUDA Memory Issue even with quantized model","comments":5,"created_at":"2025-05-20T12:11:15Z"},{"number":894,"title":"Local LangGraph RAG agent with Llama 3 error","comments":5,"created_at":"2025-03-06T11:11:29Z"},{"number":963,"title":"Guided grammar api signature inquiry","comments":3,"created_at":"2025-06-12T23:05:07Z"},{"number":874,"title":"Flops counter issue","comments":3,"created_at":"2025-02-04T18:06:04Z"},{"number":781,"title":"Adding a Vision RAG Notebook to Llama Recipes","comments":3,"created_at":"2024-11-10T10:57:28Z"},{"number":1082,"title":"[Idea] Metaman-Dhyaan - Elderly Companion with Vibe + Calm Mode","comments":2,"created_at":"2026-10-04T16:27:11Z"},{"number":1072,"title":"EvalPort: a portable format for the evals_synthetic_data hallucination eval sets","comments":2,"created_at":"2026-08-23T17:04:34Z"}],"discussions":[],"latest_release":{"name":"Llama-cookbook v0.0.5 Release","tag":"v0.0.5","published_at":"2025-01-22T18:56:24Z","body":"## Llama-cookbook v0.0.5 Release Notes\r\nThis release changes the package name from `llama_recipes` to `llama_cookbook` and deprecates the `llama_recipes` package name.\r\n\r\n## Highlighted Changes\r\n---\r\n- Name: `llama_cookbook` and `pip install llama-cookbook`\r\n- Update instructions https://github.com/meta-llama/llama-cookbook/pull/852\r\n- Update src package https://github.com/meta-llama/llama-cookbook/pull/861, https://github.com/meta-llama/llama-cookbook/pull/848\r\n\r\n## What's Changed\r\n* Improve discoverability of 3.2 recipes by @subramen in https://github.com/meta-llama/llama-cookbook/pull/684\r\n* fix readme by @wukaixingxp in https://github.com/meta-llama/llama-cookbook/pull/679\r\n* fix AutoModel and bump transformers version to 4.45 by @wukaixingxp in https://github.com/meta-llama/llama-cookbook/pull/686\r\n* post1 release version bump by @mreso in https://github.com/meta-llama/llama-cookbook/pull/687\r\n* Update multi_modal_infer.py by @init27 in https://github.com/meta-llama/llama-cookbook/pull/696\r\n* Add recipe for Llama Triaging & Reporting Tool by @subramen in https://github.com/meta-llama/llama-cookbook/pull/651\r\n* Updates to accommodate OpenLLM leaderboard v2 tasks and change Meta Llama 3.1 to Llama 3.1  by @wukaixingxp in https://github.com/meta-llama/llama-cookbook/pull/639\r\n* Improve model checkpoint saving logic by @lucas-ventura in https://github.com/meta-llama/llama-cookbook/pull/691\r\n* Delete cookie by @init27 in https://github.com/meta-llama/llama-cookbook/pull/700\r\n* [Fixed] RuntimeError: probability tensor contains either inf, nan or element < 0 by @himanshushukla12 in https://github.com/meta-llama/llama-cookbook/pull/704\r\n* chore: update train_utils.py by @eltociear in https://github.com/meta-llama/llama-cookbook/pull/690\r\n* Update requirements.txt by @varunfb in https://github.com/meta-llama/llama-cookbook/pull/664\r\n* added missing word and corrected spelling by @jnfinitym in https://github.com/meta-llama/llama-cookbook/pull/707\r\n* Fix the bug when continue the peft. by @24kMengXin in https://github.com/meta-llama/llama-cookbook/pull/717\r\n* Fix link to LLM finetuning overview by @vvolhejn in https://github.com/meta-llama/llama-cookbook/pull/719\r\n* fix Colab link in quickstart_peft_finetuning.ipynb by @jgrivolla in https://github.com/meta-llama/llama-cookbook/pull/720\r\n* Fix fine-tuning training loss accumulation by @celestinoalan in https://github.com/meta-llama/llama-cookbook/pull/725\r\n* quick fix on readmes and deadlinks by @wukaixingxp in https://github.com/meta-llama/llama-cookbook/pull/729\r\n* Initial Crusoe examples to 3p_integrations recipes by @ethxnp in https://github.com/meta-llama/llama-cookbook/pull/716\r\n* Fix numpy seed in finetuning.py by @patrik-lambert in https://github.com/meta-llama/llama-cookbook/pull/728\r\n* Fix/unit test 3.2 by @mreso in https://github.com/meta-llama/llama-cookbook/pull/726\r\n* Tool Calling Tutorial and Example by @init27 in https://github.com/meta-llama/llama-cookbook/pull/697\r\n* Update wordlist.txt by @init27 in https://github.com/meta-llama/llama-cookbook/pull/736\r\n* Support converting fine-tuned llama 3.2 vision model to HF format and then local inference by @wukaixingxp in https://github.com/meta-llama/llama-cookbook/pull/737\r\n* Save the `preprocessor_config.json` and `chat_template.json` for mllama model after conversion by @wukaixingxp in https://github.com/meta-llama/llama-cookbook/pull/741\r\n* Append epoch rather than best val. loss to val_loss by @celestinoalan in https://github.com/meta-llama/llama-cookbook/pull/744\r\n* Update wordlist.txt by @init27 in https://github.com/meta-llama/llama-cookbook/pull/745\r\n* Notebook llama by @init27 in https://github.com/meta-llama/llama-cookbook/pull/739\r\n* Small notes on next steps by @init27 in https://github.com/meta-llama/llama-cookbook/pull/746\r\n* Fix minor grammatical errors by @terrchen in https://github.com/meta-llama/llama-cookbook/pull/748\r\n* Update hello_llama_cloud.ipynb by @sharmax-vikas in https://github.com/meta-llama/l","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}