[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2166":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":21,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":16,"starSnapshotCount":16,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},2166,"llama3","meta-llama\u002Fllama3","meta-llama","The official Meta Llama 3 GitHub site","",null,"Python",29281,3524,252,178,0,16,45,"Other",true,false,"main",[],"2026-06-12 02:00:38","\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002Fllama3\u002Fblob\u002Fmain\u002FLlama3_Repo.jpeg\" width=\"400\"\u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n        🤗 \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fmeta-Llama\"> Models on Hugging Face\u003C\u002Fa>&nbsp | \u003Ca href=\"https:\u002F\u002Fai.meta.com\u002Fblog\u002F\"> Blog\u003C\u002Fa>&nbsp |  \u003Ca href=\"https:\u002F\u002Fllama.meta.com\u002F\">Website\u003C\u002Fa>&nbsp | \u003Ca href=\"https:\u002F\u002Fllama.meta.com\u002Fget-started\u002F\">Get Started\u003C\u002Fa>&nbsp\n\u003Cbr>\n\n---\n\n## **Note of deprecation**\n\nThank you for developing with Llama models. As part of the Llama 3.1 release, we’ve consolidated GitHub repos and added some additional repos as we’ve expanded Llama’s functionality into being an e2e Llama Stack. Please use the following repos going forward:\n- [llama-models](https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002Fllama-models) - Central repo for the foundation models including basic utilities, model cards, license and use policies\n- [PurpleLlama](https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002FPurpleLlama) - Key component of Llama Stack focusing on safety risks and inference time mitigations \n- [llama-toolchain](https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002Fllama-toolchain) - Model development (inference\u002Ffine-tuning\u002Fsafety shields\u002Fsynthetic data generation) interfaces and canonical implementations\n- [llama-agentic-system](https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002Fllama-agentic-system) - E2E standalone Llama Stack system, along with opinionated underlying interface, that enables creation of agentic applications\n- [llama-cookbook](https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002Fllama-recipes) - Community driven scripts and integrations\n\nIf you have any questions, please feel free to file an issue on any of the above repos and we will do our best to respond in a timely manner. \n\nThank you!\n\n\n# (Deprecated) Meta Llama 3\n\nWe are unlocking the power of large language models. Our latest version of Llama is now accessible to individuals, creators, researchers, and businesses of all sizes so that they can experiment, innovate, and scale their ideas responsibly.\n\nThis release includes model weights and starting code for pre-trained and instruction-tuned Llama 3 language models — including sizes of 8B to 70B parameters.\n\nThis repository is a minimal example of loading Llama 3 models and running inference. For more detailed examples, see [llama-cookbook](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fllama-recipes\u002F).\n\n## Download\n\nTo download the model weights and tokenizer, please visit the [Meta Llama website](https:\u002F\u002Fllama.meta.com\u002Fllama-downloads\u002F) and accept our License.\n\nOnce your request is approved, you will receive a signed URL over email. Then, run the download.sh script, passing the URL provided when prompted to start the download.\n\nPre-requisites: Ensure you have `wget` and `md5sum` installed. Then run the script: `.\u002Fdownload.sh`.\n\nRemember that the links expire after 24 hours and a certain amount of downloads. You can always re-request a link if you start seeing errors such as `403: Forbidden`.\n\n### Access to Hugging Face\n\nWe also provide downloads on [Hugging Face](https:\u002F\u002Fhuggingface.co\u002Fmeta-llama), in both transformers and native `llama3` formats. To download the weights from Hugging Face, please follow these steps:\n\n- Visit one of the repos, for example [meta-llama\u002FMeta-Llama-3-8B-Instruct](https:\u002F\u002Fhuggingface.co\u002Fmeta-llama\u002FMeta-Llama-3-8B-Instruct).\n- Read and accept the license. Once your request is approved, you'll be granted access to all the Llama 3 models. Note that requests used to take up to one hour to get processed.\n- To download the original native weights to use with this repo, click on the \"Files and versions\" tab and download the contents of the `original` folder. You can also download them from the command line if you `pip install huggingface-hub`:\n\n```bash\nhuggingface-cli download meta-llama\u002FMeta-Llama-3-8B-Instruct --include \"original\u002F*\" --local-dir meta-llama\u002FMeta-Llama-3-8B-Instruct\n```\n\n- To use with transformers, the following [pipeline](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Ftransformers\u002Fen\u002Fmain_classes\u002Fpipelines) snippet will download and cache the weights:\n\n  ```python\n  import transformers\n  import torch\n\n  model_id = \"meta-llama\u002FMeta-Llama-3-8B-Instruct\"\n\n  pipeline = transformers.pipeline(\n    \"text-generation\",\n    model=\"meta-llama\u002FMeta-Llama-3-8B-Instruct\",\n    model_kwargs={\"torch_dtype\": torch.bfloat16},\n    device=\"cuda\",\n  )\n  ```\n\n## Quick Start\n\nYou can follow the steps below to get up and running with Llama 3 models quickly. These steps will let you run quick inference locally. For more examples, see the [Llama Cookbook repository](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fllama-recipes).\n\n1. Clone and download this repository in a conda env with PyTorch \u002F CUDA.\n\n2. In the top-level directory run:\n    ```bash\n    pip install -e .\n    ```\n3. Visit the [Meta Llama website](https:\u002F\u002Fllama.meta.com\u002Fllama-downloads\u002F) and register to download the model\u002Fs.\n\n4. Once registered, you will get an email with a URL to download the models. You will need this URL when you run the download.sh script.\n\n5. Once you get the email, navigate to your downloaded llama repository and run the download.sh script.\n    - Make sure to grant execution permissions to the download.sh script\n    - During this process, you will be prompted to enter the URL from the email.\n    - Do not use the “Copy Link” option; copy the link from the email manually.\n\n6. Once the model\u002Fs you want have been downloaded, you can run the model locally using the command below:\n```bash\ntorchrun --nproc_per_node 1 example_chat_completion.py \\\n    --ckpt_dir Meta-Llama-3-8B-Instruct\u002F \\\n    --tokenizer_path Meta-Llama-3-8B-Instruct\u002Ftokenizer.model \\\n    --max_seq_len 512 --max_batch_size 6\n```\n**Note**\n- Replace  `Meta-Llama-3-8B-Instruct\u002F` with the path to your checkpoint directory and `Meta-Llama-3-8B-Instruct\u002Ftokenizer.model` with the path to your tokenizer model.\n- The `–nproc_per_node` should be set to the [MP](#inference) value for the model you are using.\n- Adjust the `max_seq_len` and `max_batch_size` parameters as needed.\n- This example runs the [example_chat_completion.py](example_chat_completion.py) found in this repository, but you can change that to a different .py file.\n\n## Inference\n\nDifferent models require different model-parallel (MP) values:\n\n|  Model | MP |\n|--------|----|\n| 8B     | 1  |\n| 70B    | 8  |\n\nAll models support sequence length up to 8192 tokens, but we pre-allocate the cache according to `max_seq_len` and `max_batch_size` values. So set those according to your hardware.\n\n### Pretrained Models\n\nThese models are not finetuned for chat or Q&A. They should be prompted so that the expected answer is the natural continuation of the prompt.\n\nSee `example_text_completion.py` for some examples. To illustrate, see the command below to run it with the llama-3-8b model (`nproc_per_node` needs to be set to the `MP` value):\n\n```\ntorchrun --nproc_per_node 1 example_text_completion.py \\\n    --ckpt_dir Meta-Llama-3-8B\u002F \\\n    --tokenizer_path Meta-Llama-3-8B\u002Ftokenizer.model \\\n    --max_seq_len 128 --max_batch_size 4\n```\n\n### Instruction-tuned Models\n\nThe fine-tuned models were trained for dialogue applications. To get the expected features and performance for them, specific formatting defined in [`ChatFormat`](https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002Fllama3\u002Fblob\u002Fmain\u002Fllama\u002Ftokenizer.py#L202)\nneeds to be followed: The prompt begins with a `\u003C|begin_of_text|>` special token, after which one or more messages follow. Each message starts with the `\u003C|start_header_id|>` tag, the role `system`, `user` or `assistant`, and the `\u003C|end_header_id|>` tag. After a double newline `\\n\\n`, the message's contents follow. The end of each message is marked by the `\u003C|eot_id|>` token.\n\nYou can also deploy additional classifiers to filter out inputs and outputs that are deemed unsafe. See the llama-cookbook repo for [an example](https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002Fllama-recipes\u002Fblob\u002Fmain\u002Frecipes\u002Finference\u002Flocal_inference\u002Finference.py) of how to add a safety checker to the inputs and outputs of your inference code.\n\nExamples using llama-3-8b-chat:\n\n```\ntorchrun --nproc_per_node 1 example_chat_completion.py \\\n    --ckpt_dir Meta-Llama-3-8B-Instruct\u002F \\\n    --tokenizer_path Meta-Llama-3-8B-Instruct\u002Ftokenizer.model \\\n    --max_seq_len 512 --max_batch_size 6\n```\n\nLlama 3 is a new technology that carries potential risks with use. Testing conducted to date has not — and could not — cover all scenarios.\nTo help developers address these risks, we have created the [Responsible Use Guide](https:\u002F\u002Fai.meta.com\u002Fstatic-resource\u002Fresponsible-use-guide\u002F).\n\n## Issues\n\nPlease report any software “bug” or other problems with the models through one of the following means:\n- Reporting issues with the model: [https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002Fllama3\u002Fissues](https:\u002F\u002Fgithub.com\u002Fmeta-llama\u002Fllama3\u002Fissues)\n- Reporting risky content generated by the model: [developers.facebook.com\u002Fllama_output_feedback](http:\u002F\u002Fdevelopers.facebook.com\u002Fllama_output_feedback)\n- Reporting bugs and security concerns: [facebook.com\u002Fwhitehat\u002Finfo](http:\u002F\u002Ffacebook.com\u002Fwhitehat\u002Finfo)\n\n## Model Card\nSee [MODEL_CARD.md](MODEL_CARD.md).\n\n## License\n\nOur model and weights are licensed for researchers and commercial entities, upholding the principles of openness. Our mission is to empower individuals and industry through this opportunity while fostering an environment of discovery and ethical AI advancements.\n\nSee the [LICENSE](LICENSE) file, as well as our accompanying [Acceptable Use Policy](USE_POLICY.md)\n\n## Questions\n\nFor common questions, the FAQ can be found [here](https:\u002F\u002Fllama.meta.com\u002Ffaq), which will be updated over time as new questions arise.\n","Meta Llama 3 是一个提供预训练和指令调优的大规模语言模型的项目。它支持从8亿到700亿参数的不同大小模型，核心功能包括模型权重下载、加载及推理运行。采用Python开发，具备良好的社区支持与详细的使用文档。适用于个人开发者、研究者以及企业用户在自然语言处理领域进行创新实验和技术探索。注意，此仓库已不再维护，建议转向官方推荐的新仓库继续获取最新资源和支持。",2,"2026-06-11 02:48:34","top_language"]