![](\"https://img.shields.io/badge/Llama_API-Join_Waitlist-brightgreen?logo=meta\"){kind=icon}
\n![](\"https://img.shields.io/badge/Llama_API-Documentation-4BA9FE?logo=meta\"){kind=icon}
\n\n\n
\n![\"Llama](\"https://img.shields.io/badge/Llama_OSS-Model_cards-green?logo=meta\"){kind=icon}
![\"Llama](\"https://img.shields.io/badge/Llama_OSS-Documentation-4BA9FE?logo=meta\"){kind=icon}
![\"Hugging](\"https://img.shields.io/badge/Hugging_Face-meta--llama-yellow?logo=huggingface\"){kind=icon}
\n![\"Llama](\"https://img.shields.io/badge/Llama_Tools-synthetic--data--kit-orange?logo=meta\"){kind=icon}
![\"Llama](\"https://img.shields.io/badge/Llama_Tools-llama--prompt--ops-orange?logo=meta\"){kind=icon}
\n![](\"https://github.com/facebookresearch/PurpleLlama/blob/main/logo.png\"){kind=logo}
\n
\n🤗 Models on Hugging Face | Blog | Website | CyberSec Eval Paper | Llama Guard Paper \n
\n\n---\n\n# Purple Llama\n\nPurple Llama is an umbrella project that over time will bring together tools\nand evals to help the community build responsibly with open generative AI\nmodels. The initial release will include tools and evals for Cyber Security and\nInput/Output safeguards but we plan to contribute more in the near future.\n\n## Why purple?\n\nBorrowing a [concept](https://www.youtube.com/watch?v=ab_Fdp6FVDI) from the\ncybersecurity world, we believe that to truly mitigate the challenges which\ngenerative AI presents, we need to take both attack (red team) and defensive\n(blue team) postures. Purple teaming, composed of both red and blue team\nresponsibilities, is a collaborative approach to evaluating and mitigating\npotential risks and the same ethos applies to generative AI and hence our\ninvestment in Purple Llama will be comprehensive.\n\n## License\n\nComponents within the Purple Llama project will be licensed permissively enabling both research and commercial usage.\nWe believe this is a major step towards enabling community collaboration and standardizing the development and usage of trust and safety tools for generative AI development.\nMore concretely evals and benchm"},{"ref":"P5","kind":"page","title":"meta-llama/llama3 repository metadata","date":"2026-06-11T03:59:58.462954+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama3","signal_url":null,"signal_json_url":null,"text":"# meta-llama/llama3\n\nDescription: The official Meta Llama 3 GitHub site\n\nLanguage: Python\n\nLicense: NOASSERTION\n\nStars: 29281\n\nForks: 3524\n\nOpen issues: 217\n\nCreated: 2024-03-15T17:57:00Z\n\nPushed: 2025-01-26T21:39:06Z\n\nDefault branch: main\n\nFork: no\n\nArchived: yes\n\nREADME:\n
\n![](\"https://github.com/meta-llama/llama3/blob/main/Llama3_Repo.jpeg\")
\n
\n🤗 Models on Hugging Face | Blog | Website | Get Started \n
\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://github.com/meta-llama/llama-models) - Central repo for the foundation models including basic utilities, model cards, license and use policies\n- [PurpleLlama](https://github.com/meta-llama/PurpleLlama) - Key component of Llama Stack focusing on safety risks and inference time mitigations \n- [llama-toolchain](https://github.com/meta-llama/llama-toolchain) - Model development (inference/fine-tuning/safety shields/synthetic data generation) interfaces and canonical implementations\n- [llama-agentic-system](https://github.com/meta-llama/llama-agentic-system) - E2E standalone Llama Stack system, along with opinionated underlying interface, that enables creation of agentic applications\n- [llama-cookbook](https://github.com/meta-llama/llama-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# (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 respons"},{"ref":"P6","kind":"page","title":"meta-llama/llama-models repository metadata","date":"2026-06-11T03:59:58.352313+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-models","signal_url":null,"signal_json_url":null,"text":"# meta-llama/llama-models\n\nDescription: Utilities intended for use with Llama models.\n\nLanguage: Python\n\nLicense: NOASSERTION\n\nStars: 7625\n\nForks: 1386\n\nOpen issues: 204\n\nCreated: 2024-06-27T22:14:09Z\n\nPushed: 2026-02-11T16:38:31Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n
\n![](\"/Llama_Repo.jpeg\")
\n
\n🤗 Models on Hugging Face | Blog | Website | Get Started | Llama Cookbook \n
\n\n---\n\n# Llama Models\n\nLlama is an accessible, open large language model (LLM) designed for developers, researchers, and businesses to build, experiment, and responsibly scale their generative AI ideas. Part of a foundational system, it serves as a bedrock for innovation in the global community. A few key aspects:\n1. **Open access**: Easy accessibility to cutting-edge large language models, fostering collaboration and advancements among developers, researchers, and organizations\n2. **Broad ecosystem**: Llama models have been downloaded hundreds of millions of times, there are thousands of community projects built on Llama and platform support is broad from cloud providers to startups - the world is building with Llama!\n3. **Trust & safety**: Llama models are part of a comprehensive approach to trust and safety, releasing models and tools that are designed to enable community collaboration and encourage the standardization of the development and usage of trust and safety tools for generative AI\n\nOur mission is to empower individuals and industry through this opportunity while fostering an environment of discovery and ethical AI advancements. The model weights are licensed for researchers and commercial entities, upholding the principles of openness.\n\n## Llama Models\n\n[](https://pypi.org/project/llama-models/)\n[](https://discord.gg/TZAAYNVtrU"},{"ref":"P7","kind":"page","title":"meta-llama/llama-stack-ops repository metadata","date":"2026-06-11T03:59:58.323289+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-stack-ops","signal_url":null,"signal_json_url":null,"text":"# meta-llama/llama-stack-ops\n\nDescription: Ops files for https//github.com/meta-llama/llama-stack\n\nLanguage: Shell\n\nLicense: MIT\n\nStars: 17\n\nForks: 20\n\nOpen issues: 6\n\nCreated: 2025-01-28T14:34:10Z\n\nPushed: 2025-06-28T14:50:57Z\n\nDefault branch: main\n\nFork: no\n\nArchived: yes\n\nREADME:\n# Operations (CI, etc.) for Llama Stack"},{"ref":"P8","kind":"page","title":"meta-llama/llama-verifications repository metadata","date":"2026-06-11T03:59:58.258333+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-verifications","signal_url":null,"signal_json_url":null,"text":"# meta-llama/llama-verifications\n\nDescription: Functional tests and benchmarks for verifying Llama model providers.\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 27\n\nForks: 24\n\nOpen issues: 25\n\nCreated: 2025-05-13T23:02:38Z\n\nPushed: 2026-02-11T17:03:58Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Llama Verifications\n\nThis repository contains a lightweight library to verify model providers via 2 suites,\n1. Functional tests and\n2. Eval benchmarks\n\nBoth the suites can be run on any Llama Provider that offers an OpenAI-compliant Inference API.\n\n| **Type of Verification** | **Description** | **Llama Provider Expectation** |\n| --- | --- | --- |\n| **Functional Tests** | Testing inference across:
\n![](\"https://img.shields.io/pypi/v/prompt-ops.svg\")
\n
\n
![\"Hugging](\"https://img.shields.io/badge/Hugging_Face-meta--llama-yellow?logo=huggin"},{"ref":"P11","kind":"page","title":"meta-llama/llama-api-typescript){kind=icon}
)](https://npmjs.org/package/llama-api-client)\n\nThis library provides convenient access to the Llama API Client REST API from server-side TypeScript or JavaScript.\n\nThe REST API documentation can be found on [llama.developer.meta.com](https://llama.developer.meta.com/docs). The full API of this library can be found in [api.md](api.md).\n\nIt is generated with [Stainless](https://www.stainless.com/).\n\n## Installation\n\n```sh\nnpm install llama-api-client\n```\n\n## Usage\n\nThe full API of this library can be found in [api.md](api.md).\n\n\n```js\nimport LlamaAPIClient from 'llama-api-client';\n\nconst client = new LlamaAPIClient({\napiKey: process.env['LLAMA_API_KEY'], // This is the default and can be omitted\n});\n\nconst createChatCompletionResponse = await client.chat.completions.create({\nmessages: [{ content: 'string', role: 'user' }],\nmodel: 'model',\n});\n\nconsole.log(createChatCompletionResponse.completion_message);\n```\n\n## Streaming responses\n\nWe provide support for streaming responses using Server Sent Events (SSE).\n\n```ts\nimport LlamaAPIClient from 'llama-api-client';\n\nconst client = new LlamaAPIClient();\n\nconst stream = await client.chat.completions.create({\nmessages: [{ content: 'string', role: 'user' }],\nmodel: 'model',\nstream: true,\n});\nfor await (const createChatCompletionResponseStreamChunk of stream) {\nconsole.log(createChatCompletionResponseStreamChunk);\n}\n```\n\nIf you need to cancel a stream, you can `break` from the loop\nor call `stream.controller.abort()`.\n\n### Request & Response types\n\nThis library includes TypeScript definitions for all request params and response fields. You may import and use them like so:\n\n\n```ts\nimport LlamaAPIClient from 'llama-api-client';\n\nconst client = new LlamaAPIClient({\nap"},{"ref":"P12","kind":"page","title":"meta-llama/synthetic-data-kit repository metadata","date":"2026-06-11T03:59:57.537835+00:00","date_source":null,"source_url":"https://github.com/meta-llama/synthetic-data-kit","signal_url":null,"signal_json_url":null,"text":"# meta-llama/synthetic-data-kit\n\nDescription: Tool for generating high quality Synthetic datasets\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 1597\n\nForks: 219\n\nOpen issues: 48\n\nCreated: 2025-03-27T06:40:42Z\n\nPushed: 2025-10-28T20:10:55Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Synthetic Data Kit\n\nTool for generating high-quality synthetic datasets to fine-tune LLMs.\n\nGenerate Reasoning Traces, QA Pairs, save them to a fine-tuning format with a simple CLI.\n\n> [Checkout our guide on using the tool to unlock task-specific reasoning in Llama-3 family](https://github.com/meta-llama/synthetic-data-kit/tree/main/use-cases/adding_reasoning_to_llama_3)\n\n# What does Synthetic Data Kit offer? \n\nFine-Tuning Large Language Models is easy. There are many mature tools that you can use to fine-tune Llama model family using various post-training techniques.\n\n### Why target data preparation?\n\nMultiple tools support standardized formats. However, most of the times your dataset is not structured in \"user\", \"assistant\" threads or in a certain format that plays well with a fine-tuning packages. \n\nThis toolkit simplifies the journey of:\n\n- Using a LLM (vLLM or any local/external API endpoint) to generate examples\n- Modular 4 command flow\n- Converting your existing files to fine-tuning friendly formats\n- Creating synthetic datasets\n- Supporting various formats of post-training fine-tuning\n\n# How does Synthetic Data Kit offer it? \n\nThe tool is designed to follow a simple CLI structure with 4 commands:\n\n- `ingest` various file formats\n- `create` your fine-tuning format: `QA` pairs, `QA` pairs with CoT, `summary` format\n- `curate`: Using Llama as a judge to curate high quality examples. \n- `save-as`: After that you can simply save these to a format that your fine-tuning workflow requires.\n\nYou can override any parameter or detail by either using the CLI or overriding the default YAML config.\n\n### Installation\n\n#### From PyPI\n\n```bash\n# Create a new environment\n\nconda create -n synthetic-data python=3.10 \n\nconda activate synthetic-data\n\npip install synthetic-data-kit\n```\n\n#### (Alternatively) From Source\n\n```bash\ngit clone https://github.com/meta-llama/synthetic-data-kit.git\ncd"},{"ref":"P13","kind":"page","title":"meta-llama/llama-cookbook v0.0.3","date":"2026-06-11T03:47:28.995053+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-cookbook/releases/tag/v0.0.3","signal_url":null,"signal_json_url":null,"text":"# Llama-recipes v.0.0.3 Release Notes\n\nRepository: meta-llama/llama-cookbook\n\nTag: v0.0.3\n\nPublished: 2024-07-23T17:43:53Z\n\nPrerelease: no\n\nRelease notes:\n## Llama 3.1 Integration\nThis release accompanies the release of [Llama 3.1](https://llama.meta.com/) which included new versions of the Llama 8B and 70B models as well as the new 405B version. To get started with the new models you can find information in the [official documentation](https://llama.meta.com/docs/overview) or the on the[ HuggingFace hub](https://huggingface.co/collections/meta-llama/llama-31-669fc079a0c406a149a5738f). Further details can also be found in the [model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md) and the [Llama 3.1 paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/). For this release we updated the documentation and made sure all components work with the new models.\n* Release update by @albertodepaola @cynikolai @mreso @subramen @tryrobbo @varunfb in [#603](https://github.com/meta-llama/llama-recipes/pull/603)\n## New Features\nWe also added new features like FSDP + QLoRA fine-tuning and H2O algorithm for long context inference.\n* Implement H2O for long context inference on summarization tasks by [@Kyriection](https://github.com/Kyriection) in [#411](https://github.com/meta-llama/llama-recipes/pull/411)\n* Resume the fine-tuning process from the previous PEFT checkpoint folder by [@wukaixingxp](https://github.com/wukaixingxp) in [#531](https://github.com/meta-llama/llama-recipes/pull/531)\n* Update hf weight conversion script to llama 3 by [@dongwang218](https://github.com/dongwang218) in [#551](https://github.com/meta-llama/llama-recipes/pull/551)\n* Adding support for FSDP+Qlora. by [@HamidShojanazeri](https://github.com/HamidShojanazeri) in [#572](https://github.com/meta-llama/llama-recipes/pull/572)\n## Additional Examples\nBesides, we added new examples to get you up and running quickly with the Llama models\n* Add Groq/Llama3 recipes (cookbook and command line examples) by [@dloman118](https://github.com/dloman118) in [#553](https://github.com/meta-llama/llama-recipes/pull/553)\n* [WIP] Peft Finetuning Quickstart N"},{"ref":"P14","kind":"page","title":"meta-llama/llama-cookbook v0.0.4","date":"2026-06-11T03:47:28.975729+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-cookbook/releases/tag/v0.0.4","signal_url":null,"signal_json_url":null,"text":"# Llama-recipes v.0.0.4 Release Notes\n\nRepository: meta-llama/llama-cookbook\n\nTag: v0.0.4\n\nPublished: 2024-09-25T18:55:29Z\n\nPrerelease: no\n\nRelease notes:\nThis release accompanies the release of [Llama 3.2](https://llama.meta.com/) which included new versions of the Llama models in sizes of 1B, 3B, 11B and 90B. To get started with the new models you can find information in the [official documentation](https://llama.meta.com/docs/overview) or the on the[ HuggingFace hub](https://huggingface.co/collections/meta-llama/llama-32-66f448ffc8c32f949b04c8cf). Further details can also be found in the [model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md) and the [The Llama 3 Herd of Models](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/) paper. For this release we updated the documentation and made sure all components work with the new models including multimodal finetuning.\n\n## What's Changed\n\n### Integrate Llama 3.2\n* Upstream merge by @albertodepaola in https://github.com/meta-llama/llama-recipes/pull/677\n\n### New and updated recipes\n* Adding end-to-end llama chatbot recipe using Retrieval Augmented Fine Tuning (RAFT) by @wukaixingxp in https://github.com/meta-llama/llama-recipes/pull/569\n* [WIP] adding chatbot-e2e by @HamidShojanazeri in https://github.com/meta-llama/llama-recipes/pull/462\n* [Azure] Update Azure API usage example to 3.1 by @WuhanMonkey in https://github.com/meta-llama/llama-recipes/pull/615\n* Corrected wrong order of commands by @BakungaBronson in https://github.com/meta-llama/llama-recipes/pull/602\n* Fill in one sentence in the prompt guard tutorial. by @cynikolai in https://github.com/meta-llama/llama-recipes/pull/609\n* Llamaguard notebook colab link fix by @tryrobbo in https://github.com/meta-llama/llama-recipes/pull/619\n* Updating llama 3 references to 3.1 model by @init27 in https://github.com/meta-llama/llama-recipes/pull/632\n* recipes/quickstart/Getting_to_know_Llama.ipynb, typo fix lama -> llama line 127 by @cselip in https://github.com/meta-llama/llama-recipes/pull/635\n* Update hello_llama_cloud.ipynb by @MrDlt in https://github.com/meta-llama/llama-recipes/pull/584\n* Update hel"},{"ref":"P15","kind":"page","title":"meta-llama/llama-cookbook v0.0.4.post1","date":"2026-06-11T03:47:28.890926+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-cookbook/releases/tag/v0.0.4.post1","signal_url":null,"signal_json_url":null,"text":"# Llama-recipes v.0.0.4.post1 Release Notes\n\nRepository: meta-llama/llama-cookbook\n\nTag: v0.0.4.post1\n\nPublished: 2024-09-26T19:32:55Z\n\nPrerelease: no\n\nRelease notes:\nThis release import bug fixes and some doc changes.\n\n## What's Changed\n* Improve discoverability of 3.2 recipes by @subramen in https://github.com/meta-llama/llama-recipes/pull/684\n* fix readme by @wukaixingxp in https://github.com/meta-llama/llama-recipes/pull/679\n* fix AutoModel and bump transformers version to 4.45 by @wukaixingxp in https://github.com/meta-llama/llama-recipes/pull/686\n* post1 release version bump by @mreso in https://github.com/meta-llama/llama-recipes/pull/687"},{"ref":"P16","kind":"page","title":"meta-llama/llama-cookbook v0.0.5","date":"2026-06-11T03:47:28.886301+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-cookbook/releases/tag/v0.0.5","signal_url":null,"signal_json_url":null,"text":"# Llama-cookbook v0.0.5 Release\n\nRepository: meta-llama/llama-cookbook\n\nTag: v0.0.5\n\nPublished: 2025-01-22T18:56:24Z\n\nPrerelease: no\n\nRelease notes:\n## Llama-cookbook v0.0.5 Release Notes\nThis release changes the package name from `llama_recipes` to `llama_cookbook` and deprecates the `llama_recipes` package name.\n\n## Highlighted Changes\n---\n- Name: `llama_cookbook` and `pip install llama-cookbook`\n- Update instructions https://github.com/meta-llama/llama-cookbook/pull/852\n- Update src package https://github.com/meta-llama/llama-cookbook/pull/861, https://github.com/meta-llama/llama-cookbook/pull/848\n\n## What's Changed\n* Improve discoverability of 3.2 recipes by @subramen in https://github.com/meta-llama/llama-cookbook/pull/684\n* fix readme by @wukaixingxp in https://github.com/meta-llama/llama-cookbook/pull/679\n* fix AutoModel and bump transformers version to 4.45 by @wukaixingxp in https://github.com/meta-llama/llama-cookbook/pull/686\n* post1 release version bump by @mreso in https://github.com/meta-llama/llama-cookbook/pull/687\n* Update multi_modal_infer.py by @init27 in https://github.com/meta-llama/llama-cookbook/pull/696\n* Add recipe for Llama Triaging & Reporting Tool by @subramen in https://github.com/meta-llama/llama-cookbook/pull/651\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\n* Improve model checkpoint saving logic by @lucas-ventura in https://github.com/meta-llama/llama-cookbook/pull/691\n* Delete cookie by @init27 in https://github.com/meta-llama/llama-cookbook/pull/700\n* [Fixed] RuntimeError: probability tensor contains either inf, nan or element < 0 by @himanshushukla12 in https://github.com/meta-llama/llama-cookbook/pull/704\n* chore: update train_utils.py by @eltociear in https://github.com/meta-llama/llama-cookbook/pull/690\n* Update requirements.txt by @varunfb in https://github.com/meta-llama/llama-cookbook/pull/664\n* added missing word and corrected spelling by @jnfinitym in https://github.com/meta-llama/llama-cookbook/pull/707\n* Fix the bug when continue the peft. by @24kMengXin in https://github.com/meta-llama/llama-cookbo"},{"ref":"P17","kind":"page","title":"meta-llama/llama-models v0.1.0","date":"2026-06-11T03:47:28.703361+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-models/releases/tag/v0.1.0","signal_url":null,"signal_json_url":null,"text":"# v0.1.0\n\nRepository: meta-llama/llama-models\n\nTag: v0.1.0\n\nPublished: 2025-01-24T17:48:23Z\n\nPrerelease: no\n\nRelease notes:\nFollowing https://github.com/meta-llama/llama-stack/releases/tag/v0.1.0"},{"ref":"P18","kind":"page","title":"meta-llama/llama-models v0.1.4","date":"2026-06-11T03:47:28.542874+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-models/releases/tag/v0.1.4","signal_url":null,"signal_json_url":null,"text":"# v0.1.4\n\nRepository: meta-llama/llama-models\n\nTag: v0.1.4\n\nPublished: 2025-02-25T00:04:44Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* fix: do not use python_tag when encoding non-code_interpreter tool_calls by @ehhuang in https://github.com/meta-llama/llama-models/pull/283\n* fix: tool_call was not encoded by @ehhuang in https://github.com/meta-llama/llama-models/pull/284\n\n**Full Changelog**: https://github.com/meta-llama/llama-models/compare/v0.1.3...v0.1.4"},{"ref":"P19","kind":"page","title":"meta-llama/llama-models v0.1.3","date":"2026-06-11T03:47:28.529826+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-models/releases/tag/v0.1.3","signal_url":null,"signal_json_url":null,"text":"# v0.1.3\n\nRepository: meta-llama/llama-models\n\nTag: v0.1.3\n\nPublished: 2025-02-14T22:11:36Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* Move all Llama Stack types to llama-stack by @ashwinb in https://github.com/meta-llama/llama-models/pull/279\n\n**Full Changelog**: https://github.com/meta-llama/llama-models/compare/v0.1.2...v0.1.3"},{"ref":"P20","kind":"page","title":"meta-llama/llama-api-python v0.2.0","date":"2026-06-11T03:47:28.473981+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-api-python/releases/tag/v0.2.0","signal_url":null,"signal_json_url":null,"text":"# v0.2.0\n\nRepository: meta-llama/llama-api-python\n\nTag: v0.2.0\n\nPublished: 2025-08-12T17:06:49Z\n\nPrerelease: no\n\nRelease notes:\n## 0.2.0 (2025-08-07)\n\nFull Changelog: [v0.1.2...v0.2.0](https://github.com/meta-llama/llama-api-python/compare/v0.1.2...v0.2.0)\n\n### Features\n\n* clean up environment call outs ([4afbd01](https://github.com/meta-llama/llama-api-python/commit/4afbd01ed735b93d8b4c8c282881f2b78673995c))\n* **client:** support file upload requests ([ec42e80](https://github.com/meta-llama/llama-api-python/commit/ec42e80b6249b3af1f3474ad4fba61d669ec0035))\n\n### Bug Fixes\n\n* **api:** remove chat completion request model ([94c4e9f](https://github.com/meta-llama/llama-api-python/commit/94c4e9fd500502781a0f6e30715ecbd134d015db))\n* **client:** don't send Content-Type header on GET requests ([efec88a](https://github.com/meta-llama/llama-api-python/commit/efec88aa519948ea58ee629507cd91e9af90c1c8))\n* **parsing:** correctly handle nested discriminated unions ([b627686](https://github.com/meta-llama/llama-api-python/commit/b6276863bea64a7127cdb71b6fbb02534d2e762b))\n* **parsing:** ignore empty metadata ([d6ee851](https://github.com/meta-llama/llama-api-python/commit/d6ee85101e3e69c2768761e1187b8d33ee4e3762))\n* **parsing:** parse extra field types ([f03ca22](https://github.com/meta-llama/llama-api-python/commit/f03ca2286018699dd29b964e9cbc1a66699ef59e))\n\n### Chores\n\n* add examples ([abfa065](https://github.com/meta-llama/llama-api-python/commit/abfa06572191caeaa33603c846d5953aa453521e))\n* **internal:** bump pinned h11 dep ([d40e1b1](https://github.com/meta-llama/llama-api-python/commit/d40e1b1d736ec5e5fe7e3c65ace9c5d65d038081))\n* **internal:** fix ruff target version ([c900ebc](https://github.com/meta-llama/llama-api-python/commit/c900ebc528a5f21e76f4742556577bbf33060f1c))\n* **package:** mark python 3.13 as supported ([ef5bc36](https://github.com/meta-llama/llama-api-python/commit/ef5bc36693fa419e3d865e97cae97e7f5df19b1a))\n* **project:** add settings file for vscode ([e310380](https://github.com/meta-llama/llama-api-python/commit/e3103801d608df4cff07da4e3eaae72df1391626))\n* **readme:** fix version rendering on pypi ([786f9fb](https://github.com/meta-llama/llama-api-python/"},{"ref":"P21","kind":"page","title":"meta-llama/llama-models v0.2.0","date":"2026-06-11T03:47:28.436505+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-models/releases/tag/v0.2.0","signal_url":null,"signal_json_url":null,"text":"# v0.2.0\n\nRepository: meta-llama/llama-models\n\nTag: v0.2.0\n\nPublished: 2025-04-05T19:02:56Z\n\nPrerelease: no\n\nRelease notes:\nLlama 4 Support ( https://www.llama.com )"},{"ref":"P22","kind":"page","title":"meta-llama/llama-verifications v0.1.1","date":"2026-06-11T03:47:28.254785+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-verifications/releases/tag/v0.1.1","signal_url":null,"signal_json_url":null,"text":"# Release 0.1.1\n\nRepository: meta-llama/llama-verifications\n\nTag: v0.1.1\n\nPublished: 2025-08-15T19:36:44Z\n\nPrerelease: no\n\nRelease notes:\nStable release for llama-verifications\n\n## Changes\n- GitHub release created\n\n## Installation\n```bash\\ngit clone https://github.com/meta-llama/llama-verifications.git\\ncd llama-verifications\\nuv tool install --with-editable . --python 3.12 llama-verifications\\n```"},{"ref":"P23","kind":"page","title":"meta-llama/llama-api-python v0.3.0","date":"2026-06-11T03:47:28.072953+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-api-python/releases/tag/v0.3.0","signal_url":null,"signal_json_url":null,"text":"# v0.3.0\n\nRepository: meta-llama/llama-api-python\n\nTag: v0.3.0\n\nPublished: 2025-08-27T00:59:07Z\n\nPrerelease: no\n\nRelease notes:\n## 0.3.0 (2025-08-26)\n\nFull Changelog: [v0.2.0...v0.3.0](https://github.com/meta-llama/llama-api-python/compare/v0.2.0...v0.3.0)\n\n### Features\n\n* custom patch to handle exception during stream chunk ([7549f0b](https://github.com/meta-llama/llama-api-python/commit/7549f0b38d85143f984191bf9ff1f353f787fa50))\n\n### Chores\n\n* **internal:** change ci workflow machines ([37dd39f](https://github.com/meta-llama/llama-api-python/commit/37dd39fe156f7ed0f36101d014a4983498a10a27))\n* **internal:** codegen related update ([cae389f](https://github.com/meta-llama/llama-api-python/commit/cae389f98552280557b2f73d0b146e159764a5a9))\n* **internal:** update comment in script ([20ab448](https://github.com/meta-llama/llama-api-python/commit/20ab4484b71a0e9c555d28de0b8fbd59246851ac))\n* run lint ([dc7d5a7](https://github.com/meta-llama/llama-api-python/commit/dc7d5a768eccf8c9d6faaac3585e7e09a611db02))\n* update @stainless-api/prism-cli to v5.15.0 ([8e77df5](https://github.com/meta-llama/llama-api-python/commit/8e77df5e5778b55bda86a38735fb1426ae3a02a4))\n* update github action ([3dab72d](https://github.com/meta-llama/llama-api-python/commit/3dab72dc5b6fc8ad8f9b9d72f25e155a7e22a857))"},{"ref":"P24","kind":"page","title":"meta-llama/llama-api-typescript v0.2.0","date":"2026-06-11T03:47:28.071601+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-api-typescript/releases/tag/v0.2.0","signal_url":null,"signal_json_url":null,"text":"# v0.2.0\n\nRepository: meta-llama/llama-api-typescript\n\nTag: v0.2.0\n\nPublished: 2025-08-27T01:47:20Z\n\nPrerelease: no\n\nRelease notes:\n## 0.2.0 (2025-08-23)\n\nFull Changelog: [v0.1.5...v0.2.0](https://github.com/meta-llama/llama-api-typescript/compare/v0.1.5...v0.2.0)\n\n### Features\n\n* **mcp:** add code execution tool ([9e72409](https://github.com/meta-llama/llama-api-typescript/commit/9e72409e9733834fef300693b79bf7cf13506f66))\n\n### Chores\n\n* add package to package.json ([5a0ff68](https://github.com/meta-llama/llama-api-typescript/commit/5a0ff68bee3ca23debc141ee714480f4275338f1))\n* **client:** qualify global Blob ([ec13a74](https://github.com/meta-llama/llama-api-typescript/commit/ec13a749bb8be01f0ed685cf76a88b5d8af28181))\n* **deps:** update dependency @types/node to v20.17.58 ([69d5447](https://github.com/meta-llama/llama-api-typescript/commit/69d5447e462c32017d1f693a74045ef52645b7c5))\n* **internal:** formatting change ([cc8da4d](https://github.com/meta-llama/llama-api-typescript/commit/cc8da4d239d7221c8db5c9482b36349f07db2d48))\n* update CI script ([8bad679](https://github.com/meta-llama/llama-api-typescript/commit/8bad6792313b36c236bfe6020c533bd8dd517d8c))"},{"ref":"P25","kind":"page","title":"meta-llama/llama-api-typescript v0.2.1","date":"2026-06-11T03:47:28.007345+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-api-typescript/releases/tag/v0.2.1","signal_url":null,"signal_json_url":null,"text":"# v0.2.1\n\nRepository: meta-llama/llama-api-typescript\n\nTag: v0.2.1\n\nPublished: 2025-09-03T20:45:14Z\n\nPrerelease: no\n\nRelease notes:\n## 0.2.1 (2025-08-28)\n\nFull Changelog: [v0.2.0...v0.2.1](https://github.com/meta-llama/llama-api-typescript/compare/v0.2.0...v0.2.1)\n\n### Chores\n\n* **internal:** update global Error reference ([e541458](https://github.com/meta-llama/llama-api-typescript/commit/e541458a4c32012d8ca36af03f60a21dd9e8d679))"},{"ref":"P26","kind":"page","title":"meta-llama/llama-verifications v0.1.20.1.2rc2","date":"2026-06-11T03:47:27.923336+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-verifications/releases/tag/v0.1.20.1.2rc2","signal_url":null,"signal_json_url":null,"text":"# Release 0.1.20.1.2rc2\n\nRepository: meta-llama/llama-verifications\n\nTag: v0.1.20.1.2rc2\n\nPublished: 2025-09-09T04:28:20Z\n\nPrerelease: yes\n\nRelease notes:\nRelease candidate for llama-verifications\n\n## Changes\n- GitHub release created\n\n## Installation\n```bash\\ngit clone https://github.com/meta-llama/llama-verifications.git\\ncd llama-verifications\\nuv tool install --with-editable . --python 3.12 llama-verifications\\n```"},{"ref":"P27","kind":"page","title":"meta-llama/llama-api-python v0.4.0","date":"2026-06-11T03:47:27.825432+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-api-python/releases/tag/v0.4.0","signal_url":null,"signal_json_url":null,"text":"# v0.4.0\n\nRepository: meta-llama/llama-api-python\n\nTag: v0.4.0\n\nPublished: 2025-09-17T21:03:43Z\n\nPrerelease: no\n\nRelease notes:\n## 0.4.0 (2025-09-16)\n\nFull Changelog: [v0.3.0...v0.4.0](https://github.com/meta-llama/llama-api-python/compare/v0.3.0...v0.4.0)\n\n### Features\n\n* improve future compat with pydantic v3 ([648fe7b](https://github.com/meta-llama/llama-api-python/commit/648fe7be582adb6c50f73d24b32f6c9abdf88d73))\n* **types:** replace List[str] with SequenceNotStr in params ([565a26d](https://github.com/meta-llama/llama-api-python/commit/565a26da9736a27ec88e1139e70569e3ba084b3a))\n\n### Bug Fixes\n\n* avoid newer type syntax ([b9bfeb3](https://github.com/meta-llama/llama-api-python/commit/b9bfeb3df2528b0c77017e9b1b50bcd54bf731bb))\n\n### Chores\n\n* **internal:** add Sequence related utils ([909f85f](https://github.com/meta-llama/llama-api-python/commit/909f85f12cb61ee164764bca656c0b574b0bcd2a))\n* **internal:** move mypy configurations to `pyproject.toml` file ([68106c6](https://github.com/meta-llama/llama-api-python/commit/68106c6af940f1cbbbafae6dc0de999e1f853325))\n* **internal:** update pydantic dependency ([9ad2fea](https://github.com/meta-llama/llama-api-python/commit/9ad2fea856c3470b20b89ddd033614eee40c0ea0))\n* **internal:** update pyright exclude list ([203a1a1](https://github.com/meta-llama/llama-api-python/commit/203a1a1d8a74ece63939e25ec0a1b91c42706119))\n* **tests:** simplify `get_platform` test ([21f3cd5](https://github.com/meta-llama/llama-api-python/commit/21f3cd5b775c2963be3d13ccfc59273c163fdfbc))"},{"ref":"P28","kind":"page","title":"meta-llama/llama-api-typescript v0.2.2","date":"2026-06-11T03:47:27.641828+00:00","date_source":null,"source_url":"https://github.com/meta-llama/llama-api-typescript/releases/tag/v0.2.2","signal_url":null,"signal_json_url":null,"text":"# v0.2.2\n\nRepository: meta-llama/llama-api-typescript\n\nTag: v0.2.2\n\nPublished: 2025-09-17T22:05:07Z\n\nPrerelease: no\n\nRelease notes:\n## 0.2.2 (2025-09-08)\n\nFull Changelog: [v0.2.1...v0.2.2](https://github.com/meta-llama/llama-api-typescript/compare/v0.2.1...v0.2.2)\n\n### Bug Fixes\n\n* coerce nullable values to undefined ([c804bb5](https://github.com/meta-llama/llama-api-typescript/commit/c804bb5d65dc9753e664617ab7b7585703809451))\n\n### Chores\n\n* ci build action ([22ba16c](https://github.com/meta-llama/llama-api-typescript/commit/22ba16c74d64ede49ad2134ead57571ce82a2952))"},{"ref":"E1","kind":"event","title":"meta-llama/Llama-3.1-8B-Instruct","date":"2024-07-18T08:56:00+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct","signal_url":"https://onlylabs.fyi/signals/9e775cc4-d169-40db-89a2-ba0c71938251","signal_json_url":"https://onlylabs.fyi/signals/9e775cc4-d169-40db-89a2-ba0c71938251/signal.json","text":"model_released · meta-llama/Llama-3.1-8B-Instruct · signal_desk=releases · occurred_at=2024-07-18T08:56:00+00:00 · url=https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct · hf_downloads=9891622 · hf_likes=6048 · hf_params=8030261248 · pipeline=text-generation · license=llama3.1 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E2","kind":"event","title":"meta-llama/Llama-3.3-70B-Instruct","date":"2024-11-26T16:08:47+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","signal_url":"https://onlylabs.fyi/signals/ddcd63c6-416b-4562-aff3-8fbcc2e4a649","signal_json_url":"https://onlylabs.fyi/signals/ddcd63c6-416b-4562-aff3-8fbcc2e4a649/signal.json","text":"model_released · meta-llama/Llama-3.3-70B-Instruct · signal_desk=releases · occurred_at=2024-11-26T16:08:47+00:00 · url=https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct · hf_downloads=667240 · hf_likes=2813 · hf_params=70553706496 · pipeline=text-generation · license=llama3.3 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E3","kind":"event","title":"meta-llama/Llama-3.2-1B","date":"2024-09-18T15:03:14+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-1B","signal_url":"https://onlylabs.fyi/signals/6c9b1654-449e-48cb-9f25-9c5fba2aaa9c","signal_json_url":"https://onlylabs.fyi/signals/6c9b1654-449e-48cb-9f25-9c5fba2aaa9c/signal.json","text":"model_released · meta-llama/Llama-3.2-1B · signal_desk=releases · occurred_at=2024-09-18T15:03:14+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-1B · hf_downloads=2097743 · hf_likes=2444 · hf_params=1235814400 · pipeline=text-generation · license=llama3.2"},{"ref":"E4","kind":"event","title":"meta-llama/Llama-3.2-3B-Instruct","date":"2024-09-18T15:19:20+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct","signal_url":"https://onlylabs.fyi/signals/80334c4e-5b2c-4e3b-b1d4-23475e2e1773","signal_json_url":"https://onlylabs.fyi/signals/80334c4e-5b2c-4e3b-b1d4-23475e2e1773/signal.json","text":"model_released · meta-llama/Llama-3.2-3B-Instruct · signal_desk=releases · occurred_at=2024-09-18T15:19:20+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct · hf_downloads=1472295 · hf_likes=2217 · hf_params=3212749824 · pipeline=text-generation · license=llama3.2"},{"ref":"E5","kind":"event","title":"meta-llama/Llama-3.2-1B-Instruct","date":"2024-09-18T15:12:47+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct","signal_url":"https://onlylabs.fyi/signals/53caec85-e96d-4546-8e73-e8bce494f223","signal_json_url":"https://onlylabs.fyi/signals/53caec85-e96d-4546-8e73-e8bce494f223/signal.json","text":"model_released · meta-llama/Llama-3.2-1B-Instruct · signal_desk=releases · occurred_at=2024-09-18T15:12:47+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct · hf_downloads=7398970 · hf_likes=1471 · hf_params=1235814400 · pipeline=text-generation · license=llama3.2"},{"ref":"E6","kind":"event","title":"meta-llama/Llama-3.2-11B-Vision-Instruct","date":"2024-09-18T16:47:28+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct","signal_url":"https://onlylabs.fyi/signals/1719384b-2f93-4617-9335-f37aaf83e824","signal_json_url":"https://onlylabs.fyi/signals/1719384b-2f93-4617-9335-f37aaf83e824/signal.json","text":"model_released · meta-llama/Llama-3.2-11B-Vision-Instruct · signal_desk=releases · occurred_at=2024-09-18T16:47:28+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct · hf_downloads=149910 · hf_likes=1601 · hf_params=10670220835 · pipeline=image-text-to-text · license=llama3.2"},{"ref":"E7","kind":"event","title":"meta-llama/Llama-4-Scout-17B-16E-Instruct","date":"2025-04-02T13:34:17+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct","signal_url":"https://onlylabs.fyi/signals/c055c256-8f25-49b4-9b7b-0890500fd83e","signal_json_url":"https://onlylabs.fyi/signals/c055c256-8f25-49b4-9b7b-0890500fd83e/signal.json","text":"model_released · meta-llama/Llama-4-Scout-17B-16E-Instruct · signal_desk=releases · occurred_at=2025-04-02T13:34:17+00:00 · url=https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct · hf_downloads=426695 · hf_likes=1304 · hf_params=108641793536 · pipeline=image-text-to-text · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E8","kind":"event","title":"meta-llama/Llama-3.2-3B","date":"2024-09-18T15:23:48+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-3B","signal_url":"https://onlylabs.fyi/signals/22cb1e1d-a8a4-4281-bb44-6ee88cc6c491","signal_json_url":"https://onlylabs.fyi/signals/22cb1e1d-a8a4-4281-bb44-6ee88cc6c491/signal.json","text":"model_released · meta-llama/Llama-3.2-3B · signal_desk=releases · occurred_at=2024-09-18T15:23:48+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-3B · hf_downloads=884590 · hf_likes=811 · hf_params=3212749824 · pipeline=text-generation · license=llama3.2"},{"ref":"E9","kind":"event","title":"meta-llama/Llama-3.1-405B-Instruct","date":"2024-07-16T18:24:44+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct","signal_url":"https://onlylabs.fyi/signals/9892b108-e3a3-4ea4-9a7b-be76db9bcb61","signal_json_url":"https://onlylabs.fyi/signals/9892b108-e3a3-4ea4-9a7b-be76db9bcb61/signal.json","text":"model_released · meta-llama/Llama-3.1-405B-Instruct · signal_desk=releases · occurred_at=2024-07-16T18:24:44+00:00 · url=https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct · hf_downloads=198845 · hf_likes=595 · hf_params=405853388800 · pipeline=text-generation · license=llama3.1 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E10","kind":"event","title":"meta-llama/Llama-3.2-11B-Vision","date":"2024-09-18T16:46:21+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-11B-Vision","signal_url":"https://onlylabs.fyi/signals/6b84bc8b-5884-4181-90b5-13c658e2d691","signal_json_url":"https://onlylabs.fyi/signals/6b84bc8b-5884-4181-90b5-13c658e2d691/signal.json","text":"model_released · meta-llama/Llama-3.2-11B-Vision · signal_desk=releases · occurred_at=2024-09-18T16:46:21+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-11B-Vision · hf_downloads=7703 · hf_likes=589 · hf_params=10642941475 · pipeline=image-text-to-text · license=llama3.2"},{"ref":"E11","kind":"event","title":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","date":"2025-04-01T22:17:20+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct","signal_url":"https://onlylabs.fyi/signals/df59a253-73cf-4d92-b7f7-d10ba0e2e0ec","signal_json_url":"https://onlylabs.fyi/signals/df59a253-73cf-4d92-b7f7-d10ba0e2e0ec/signal.json","text":"model_released · meta-llama/Llama-4-Maverick-17B-128E-Instruct · signal_desk=releases · occurred_at=2025-04-01T22:17:20+00:00 · url=https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct · hf_downloads=27859 · hf_likes=493 · hf_params=401583781376 · pipeline=image-text-to-text · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E12","kind":"event","title":"meta-llama/Prompt-Guard-86M","date":"2024-07-21T19:18:13+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Prompt-Guard-86M","signal_url":"https://onlylabs.fyi/signals/c763803b-0228-4c85-af32-e74f0858b0f2","signal_json_url":"https://onlylabs.fyi/signals/c763803b-0228-4c85-af32-e74f0858b0f2/signal.json","text":"model_released · meta-llama/Prompt-Guard-86M · signal_desk=releases · occurred_at=2024-07-21T19:18:13+00:00 · url=https://huggingface.co/meta-llama/Prompt-Guard-86M · hf_downloads=445396 · hf_likes=338 · hf_params=278811651 · pipeline=text-classification · license=llama3.1"},{"ref":"E13","kind":"event","title":"meta-llama/Llama-3.2-90B-Vision-Instruct","date":"2024-09-19T16:03:11+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct","signal_url":"https://onlylabs.fyi/signals/98740e5e-3c82-4a85-8032-52cff4091394","signal_json_url":"https://onlylabs.fyi/signals/98740e5e-3c82-4a85-8032-52cff4091394/signal.json","text":"model_released · meta-llama/Llama-3.2-90B-Vision-Instruct · signal_desk=releases · occurred_at=2024-09-19T16:03:11+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct · hf_downloads=869 · hf_likes=358 · hf_params=88593355323 · pipeline=image-text-to-text · license=llama3.2"},{"ref":"E14","kind":"event","title":"meta-llama/Llama-Guard-3-8B","date":"2024-07-22T08:10:45+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-Guard-3-8B","signal_url":"https://onlylabs.fyi/signals/6189f7b3-ffaa-4dbf-b50a-feecdb951f6c","signal_json_url":"https://onlylabs.fyi/signals/6189f7b3-ffaa-4dbf-b50a-feecdb951f6c/signal.json","text":"model_released · meta-llama/Llama-Guard-3-8B · signal_desk=releases · occurred_at=2024-07-22T08:10:45+00:00 · url=https://huggingface.co/meta-llama/Llama-Guard-3-8B · hf_downloads=53099 · hf_likes=299 · hf_params=8030261248 · pipeline=text-generation · license=llama3.1 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E15","kind":"event","title":"meta-llama/llama","date":"2023-02-14T09:29:12+00:00","date_source":"source","source_url":"https://github.com/meta-llama/llama","signal_url":"https://onlylabs.fyi/signals/3c5edeba-2ddf-4c4a-b942-7cd2185e16ef","signal_json_url":"https://onlylabs.fyi/signals/3c5edeba-2ddf-4c4a-b942-7cd2185e16ef/signal.json","text":"repo_new · meta-llama/llama · signal_desk=repos · occurred_at=2023-02-14T09:29:12+00:00 · url=https://github.com/meta-llama/llama · stars=59453 · data_radar_lanes=Infrastructure · data_radar_terms=inference · data_radar_reason=Meta AI (Llama) has a repo signal matching infrastructure. · raw={\"repo\":\"meta-llama/llama\",\"description\":\"Inference code for Llama models\",\"language\":\"Python\"}"},{"ref":"E16","kind":"event","title":"meta-llama/Llama-4-Scout-17B-16E","date":"2025-04-02T17:03:27+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E","signal_url":"https://onlylabs.fyi/signals/26b88130-8419-46b6-9953-2afc5145017a","signal_json_url":"https://onlylabs.fyi/signals/26b88130-8419-46b6-9953-2afc5145017a/signal.json","text":"model_released · meta-llama/Llama-4-Scout-17B-16E · signal_desk=releases · occurred_at=2025-04-02T17:03:27+00:00 · url=https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E · hf_downloads=14110 · hf_likes=249 · hf_params=108641793536 · pipeline=image-text-to-text · license=other"},{"ref":"E17","kind":"event","title":"meta-llama/llama3","date":"2024-03-15T17:57:00+00:00","date_source":"source","source_url":"https://github.com/meta-llama/llama3","signal_url":"https://onlylabs.fyi/signals/13175982-e884-4a82-a87d-3ba60e750954","signal_json_url":"https://onlylabs.fyi/signals/13175982-e884-4a82-a87d-3ba60e750954/signal.json","text":"repo_new · meta-llama/llama3 · signal_desk=repos · occurred_at=2024-03-15T17:57:00+00:00 · url=https://github.com/meta-llama/llama3 · stars=29281 · hn=3 points/0 comments · raw={\"repo\":\"meta-llama/llama3\",\"description\":\"The official Meta Llama 3 GitHub site\",\"language\":\"Python\"}"},{"ref":"E18","kind":"event","title":"meta-llama/Llama-Prompt-Guard-2-86M","date":"2025-04-28T07:16:35+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-86M","signal_url":"https://onlylabs.fyi/signals/319817b9-00a9-4360-8193-2b1d31e7dfc5","signal_json_url":"https://onlylabs.fyi/signals/319817b9-00a9-4360-8193-2b1d31e7dfc5/signal.json","text":"model_released · meta-llama/Llama-Prompt-Guard-2-86M · signal_desk=releases · occurred_at=2025-04-28T07:16:35+00:00 · url=https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-86M · hf_downloads=119587 · hf_likes=139 · hf_params=278810882 · pipeline=text-classification · license=other"},{"ref":"E19","kind":"event","title":"meta-llama/Llama-3.2-90B-Vision","date":"2024-09-19T11:32:34+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-90B-Vision","signal_url":"https://onlylabs.fyi/signals/75496ecb-0748-41ed-a9ce-c7f9ca34ff0e","signal_json_url":"https://onlylabs.fyi/signals/75496ecb-0748-41ed-a9ce-c7f9ca34ff0e/signal.json","text":"model_released · meta-llama/Llama-3.2-90B-Vision · signal_desk=releases · occurred_at=2024-09-19T11:32:34+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-90B-Vision · hf_downloads=528 · hf_likes=134 · hf_params=88593355323 · pipeline=image-text-to-text · license=llama3.2"},{"ref":"E20","kind":"event","title":"meta-llama/Llama-Guard-3-1B","date":"2024-09-20T16:04:40+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-Guard-3-1B","signal_url":"https://onlylabs.fyi/signals/972dabaf-7288-49cb-8861-91f6f986cc2b","signal_json_url":"https://onlylabs.fyi/signals/972dabaf-7288-49cb-8861-91f6f986cc2b/signal.json","text":"model_released · meta-llama/Llama-Guard-3-1B · signal_desk=releases · occurred_at=2024-09-20T16:04:40+00:00 · url=https://huggingface.co/meta-llama/Llama-Guard-3-1B · hf_downloads=40597 · hf_likes=109 · hf_params=1498482688 · pipeline=text-generation · license=llama3.2"},{"ref":"E21","kind":"event","title":"meta-llama/Llama-Guard-4-12B","date":"2025-04-23T11:30:25+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-Guard-4-12B","signal_url":"https://onlylabs.fyi/signals/052f291b-b2da-4e38-a912-3015a9fc0c76","signal_json_url":"https://onlylabs.fyi/signals/052f291b-b2da-4e38-a912-3015a9fc0c76/signal.json","text":"model_released · meta-llama/Llama-Guard-4-12B · signal_desk=releases · occurred_at=2025-04-23T11:30:25+00:00 · url=https://huggingface.co/meta-llama/Llama-Guard-4-12B · hf_downloads=143168 · hf_likes=102 · hf_params=12001097216 · pipeline=image-text-to-text · license=other"},{"ref":"E22","kind":"event","title":"meta-llama/Llama-4-Maverick-17B-128E","date":"2025-04-02T17:35:27+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E","signal_url":"https://onlylabs.fyi/signals/c7283b2a-0090-4526-9e2c-34dde95ac80f","signal_json_url":"https://onlylabs.fyi/signals/c7283b2a-0090-4526-9e2c-34dde95ac80f/signal.json","text":"model_released · meta-llama/Llama-4-Maverick-17B-128E · signal_desk=releases · occurred_at=2025-04-02T17:35:27+00:00 · url=https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E · hf_downloads=1641 · hf_likes=95 · hf_params=401583781376 · pipeline=image-text-to-text · license=other"},{"ref":"E23","kind":"event","title":"meta-llama/llama-cookbook","date":"2023-07-17T07:33:48+00:00","date_source":"source","source_url":"https://github.com/meta-llama/llama-cookbook","signal_url":"https://onlylabs.fyi/signals/4421a667-c80b-4f3d-bc04-07b2c127cc19","signal_json_url":"https://onlylabs.fyi/signals/4421a667-c80b-4f3d-bc04-07b2c127cc19/signal.json","text":"repo_new · meta-llama/llama-cookbook · signal_desk=repos · occurred_at=2023-07-17T07:33:48+00:00 · url=https://github.com/meta-llama/llama-cookbook · stars=18348 · data_radar_lanes=Data demand, Infrastructure · data_radar_terms=rag, inference · data_radar_reason=Meta AI (Llama) has a repo signal matching data demand, infrastructure. · raw={\"repo\":\"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 \",\"language\":\"Jupyter Notebook\"}"},{"ref":"E24","kind":"event","title":"meta-llama/Llama-4-Maverick-17B-128E-Original","date":"2025-04-03T15:51:13+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Original","signal_url":"https://onlylabs.fyi/signals/fa3b138d-e1df-4825-b091-4dcb53d62844","signal_json_url":"https://onlylabs.fyi/signals/fa3b138d-e1df-4825-b091-4dcb53d62844/signal.json","text":"model_released · meta-llama/Llama-4-Maverick-17B-128E-Original · signal_desk=releases · occurred_at=2025-04-03T15:51:13+00:00 · url=https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Original · hf_downloads=9 · hf_likes=82 · license=other"},{"ref":"E25","kind":"event","title":"meta-llama/codellama","date":"2023-08-24T14:25:15+00:00","date_source":"source","source_url":"https://github.com/meta-llama/codellama","signal_url":"https://onlylabs.fyi/signals/f706993f-6c59-44eb-9c62-9350b354f10f","signal_json_url":"https://onlylabs.fyi/signals/f706993f-6c59-44eb-9c62-9350b354f10f/signal.json","text":"repo_new · meta-llama/codellama · signal_desk=repos · occurred_at=2023-08-24T14:25:15+00:00 · url=https://github.com/meta-llama/codellama · stars=16311 · data_radar_lanes=Infrastructure · data_radar_terms=inference · data_radar_reason=Meta AI (Llama) has a repo signal matching infrastructure. · raw={\"repo\":\"meta-llama/codellama\",\"description\":\"Inference code for CodeLlama models\",\"language\":\"Python\"}"},{"ref":"E26","kind":"event","title":"meta-llama/Llama-Guard-3-11B-Vision","date":"2024-09-20T15:42:27+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-Guard-3-11B-Vision","signal_url":"https://onlylabs.fyi/signals/2d64abae-dde6-4a36-88ce-8cd0718a28c1","signal_json_url":"https://onlylabs.fyi/signals/2d64abae-dde6-4a36-88ce-8cd0718a28c1/signal.json","text":"model_released · meta-llama/Llama-Guard-3-11B-Vision · signal_desk=releases · occurred_at=2024-09-20T15:42:27+00:00 · url=https://huggingface.co/meta-llama/Llama-Guard-3-11B-Vision · hf_downloads=2911 · hf_likes=74 · hf_params=10670220835 · pipeline=image-text-to-text · license=llama3.2"},{"ref":"E27","kind":"event","title":"meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8","date":"2024-10-23T21:30:48+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8","signal_url":"https://onlylabs.fyi/signals/5d2271d1-98db-48be-9804-409d2b20f8b7","signal_json_url":"https://onlylabs.fyi/signals/5d2271d1-98db-48be-9804-409d2b20f8b7/signal.json","text":"model_released · meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8 · signal_desk=releases · occurred_at=2024-10-23T21:30:48+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8 · hf_downloads=85 · hf_likes=72 · pipeline=text-generation · license=llama3.2 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E28","kind":"event","title":"meta-llama/Llama-4-Scout-17B-16E-Original","date":"2025-04-03T15:06:08+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Original","signal_url":"https://onlylabs.fyi/signals/9eaca9c8-1522-4c44-80d5-0f7ce6adfac3","signal_json_url":"https://onlylabs.fyi/signals/9eaca9c8-1522-4c44-80d5-0f7ce6adfac3/signal.json","text":"model_released · meta-llama/Llama-4-Scout-17B-16E-Original · signal_desk=releases · occurred_at=2025-04-03T15:06:08+00:00 · url=https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Original · hf_downloads=6 · hf_likes=60 · license=other"},{"ref":"E29","kind":"event","title":"meta-llama/Llama-4-Scout-17B-16E-Instruct-Original","date":"2025-04-03T15:39:52+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct-Original","signal_url":"https://onlylabs.fyi/signals/b653c07f-b83e-44f9-85c0-989ead1c4f7a","signal_json_url":"https://onlylabs.fyi/signals/b653c07f-b83e-44f9-85c0-989ead1c4f7a/signal.json","text":"model_released · meta-llama/Llama-4-Scout-17B-16E-Instruct-Original · signal_desk=releases · occurred_at=2025-04-03T15:39:52+00:00 · url=https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct-Original · hf_downloads=9 · hf_likes=55 · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E30","kind":"event","title":"meta-llama/Llama-Prompt-Guard-2-22M","date":"2025-04-28T07:15:58+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-22M","signal_url":"https://onlylabs.fyi/signals/de317578-151a-490a-ba5c-d45a367de8eb","signal_json_url":"https://onlylabs.fyi/signals/de317578-151a-490a-ba5c-d45a367de8eb/signal.json","text":"model_released · meta-llama/Llama-Prompt-Guard-2-22M · signal_desk=releases · occurred_at=2025-04-28T07:15:58+00:00 · url=https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-22M · hf_downloads=3886 · hf_likes=50 · hf_params=70830722 · pipeline=text-classification · license=other"},{"ref":"E31","kind":"event","title":"meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8","date":"2024-10-23T21:29:57+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8","signal_url":"https://onlylabs.fyi/signals/154c0654-e36d-4088-acaf-812a6430b27c","signal_json_url":"https://onlylabs.fyi/signals/154c0654-e36d-4088-acaf-812a6430b27c/signal.json","text":"model_released · meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8 · signal_desk=releases · occurred_at=2024-10-23T21:29:57+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8 · hf_downloads=127 · hf_likes=47 · pipeline=text-generation · license=llama3.2 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E32","kind":"event","title":"Technical Program Manager","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/technical-program-manager-seattle","signal_url":"https://onlylabs.fyi/signals/bae1deec-34e7-48c3-9a3a-f8171aa36a93","signal_json_url":"https://onlylabs.fyi/signals/bae1deec-34e7-48c3-9a3a-f8171aa36a93/signal.json","text":"job_opened · Technical Program Manager · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/technical-program-manager-seattle · raw={\"location\":\"Seattle, WA\",\"ats\":\"agent\"}"},{"ref":"E33","kind":"event","title":"Data Scientist, Analytics","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/data-scientist-analytics-menlo-park","signal_url":"https://onlylabs.fyi/signals/b177eada-7f7b-432a-a51a-2c92d42684a7","signal_json_url":"https://onlylabs.fyi/signals/b177eada-7f7b-432a-a51a-2c92d42684a7/signal.json","text":"job_opened · Data Scientist, Analytics · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/data-scientist-analytics-menlo-park · data_radar_lanes=Data demand · data_radar_terms=data · data_radar_reason=Meta AI (Llama) has a job signal matching data demand. · raw={\"location\":\"Menlo Park, CA\",\"ats\":\"agent\"}"},{"ref":"E34","kind":"event","title":"Machine Learning Engineer","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/machine-learning-engineer-palo-alto","signal_url":"https://onlylabs.fyi/signals/ee2335d5-847b-420e-8520-2406e5ac106b","signal_json_url":"https://onlylabs.fyi/signals/ee2335d5-847b-420e-8520-2406e5ac106b/signal.json","text":"job_opened · Machine Learning Engineer · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/machine-learning-engineer-palo-alto · raw={\"location\":\"Palo Alto, CA\",\"ats\":\"agent\"}"},{"ref":"E35","kind":"event","title":"Product Marketing Manager","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/product-marketing-manager-new-york","signal_url":"https://onlylabs.fyi/signals/bce64911-f0ed-4e8b-90f3-293a8ae3f970","signal_json_url":"https://onlylabs.fyi/signals/bce64911-f0ed-4e8b-90f3-293a8ae3f970/signal.json","text":"job_opened · Product Marketing Manager · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/product-marketing-manager-new-york · data_radar_lanes=Product and customer · data_radar_terms=product · data_radar_reason=Meta AI (Llama) has a job signal matching product and customer. · raw={\"location\":\"New York, NY\",\"ats\":\"agent\"}"},{"ref":"E36","kind":"event","title":"Security Engineer","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/security-engineer-menlo-park","signal_url":"https://onlylabs.fyi/signals/ddd9a03d-4b67-4646-a108-5f1186cd0be1","signal_json_url":"https://onlylabs.fyi/signals/ddd9a03d-4b67-4646-a108-5f1186cd0be1/signal.json","text":"job_opened · Security Engineer · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/security-engineer-menlo-park · data_radar_lanes=Safety and policy · data_radar_terms=security · data_radar_reason=Meta AI (Llama) has a job signal matching safety and policy. · raw={\"location\":\"Menlo Park, CA\",\"ats\":\"agent\"}"},{"ref":"E37","kind":"event","title":"Software Engineer, AR/VR","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/software-engineer-ar-vr-redmond","signal_url":"https://onlylabs.fyi/signals/99b9f85f-54b4-4f1b-8400-15bbc40eb6bd","signal_json_url":"https://onlylabs.fyi/signals/99b9f85f-54b4-4f1b-8400-15bbc40eb6bd/signal.json","text":"job_opened · Software Engineer, AR/VR · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/software-engineer-ar-vr-redmond · raw={\"location\":\"Redmond, WA\",\"ats\":\"agent\"}"},{"ref":"E38","kind":"event","title":"Software Engineer, Product","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/software-engineer-product-menlo-park","signal_url":"https://onlylabs.fyi/signals/a1241f60-d8c7-46a6-a8ee-0dcc6bf9b5d8","signal_json_url":"https://onlylabs.fyi/signals/a1241f60-d8c7-46a6-a8ee-0dcc6bf9b5d8/signal.json","text":"job_opened · Software Engineer, Product · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/software-engineer-product-menlo-park · data_radar_lanes=Product and customer · data_radar_terms=product · data_radar_reason=Meta AI (Llama) has a job signal matching product and customer. · raw={\"location\":\"Menlo Park, CA\",\"ats\":\"agent\"}"},{"ref":"E39","kind":"event","title":"Product Designer","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/product-designer-san-francisco","signal_url":"https://onlylabs.fyi/signals/e65fb853-e519-4e7b-9b4f-eecda3f6f413","signal_json_url":"https://onlylabs.fyi/signals/e65fb853-e519-4e7b-9b4f-eecda3f6f413/signal.json","text":"job_opened · Product Designer · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/product-designer-san-francisco · data_radar_lanes=Product and customer · data_radar_terms=product · data_radar_reason=Meta AI (Llama) has a job signal matching product and customer. · raw={\"location\":\"San Francisco, CA\",\"ats\":\"agent\"}"},{"ref":"E40","kind":"event","title":"Research Scientist, AI","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/research-scientist-ai-new-york","signal_url":"https://onlylabs.fyi/signals/7f46f70b-d3ed-43e1-9ca9-7ed294000b26","signal_json_url":"https://onlylabs.fyi/signals/7f46f70b-d3ed-43e1-9ca9-7ed294000b26/signal.json","text":"job_opened · Research Scientist, AI · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/research-scientist-ai-new-york · raw={\"location\":\"New York, NY\",\"ats\":\"agent\"}"},{"ref":"E41","kind":"event","title":"Software Engineer, Infrastructure","date":"2026-06-05T22:36:14.774+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/software-engineer-infrastructure-menlo-park","signal_url":"https://onlylabs.fyi/signals/dcf2ee2f-34b5-4210-a1e2-05c40b2e2c9a","signal_json_url":"https://onlylabs.fyi/signals/dcf2ee2f-34b5-4210-a1e2-05c40b2e2c9a/signal.json","text":"job_opened · Software Engineer, Infrastructure · signal_desk=hiring · occurred_at=2026-06-05T22:36:14.774+00:00 · url=https://www.metacareers.com/jobs/software-engineer-infrastructure-menlo-park · data_radar_lanes=Infrastructure · data_radar_terms=infra, infrastructure · data_radar_reason=Meta AI (Llama) has a job signal matching infrastructure. · raw={\"location\":\"Menlo Park, CA\",\"ats\":\"agent\"}"},{"ref":"E42","kind":"event","title":"Data Scientist","date":"2026-06-05T22:34:40.602+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/data-scientist","signal_url":"https://onlylabs.fyi/signals/f2fedf2d-1ba0-4d0f-b4f7-58fc53679b17","signal_json_url":"https://onlylabs.fyi/signals/f2fedf2d-1ba0-4d0f-b4f7-58fc53679b17/signal.json","text":"job_opened · Data Scientist · signal_desk=hiring · occurred_at=2026-06-05T22:34:40.602+00:00 · url=https://www.metacareers.com/jobs/data-scientist · data_radar_lanes=Data demand · data_radar_terms=data · data_radar_reason=Meta AI (Llama) has a job signal matching data demand. · raw={\"location\":\"New York, NY\",\"ats\":\"agent\"}"},{"ref":"E43","kind":"event","title":"Software Engineer","date":"2026-06-05T22:34:40.602+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/software-engineer","signal_url":"https://onlylabs.fyi/signals/3f07bb92-26aa-4c46-bf5f-765560307163","signal_json_url":"https://onlylabs.fyi/signals/3f07bb92-26aa-4c46-bf5f-765560307163/signal.json","text":"job_opened · Software Engineer · signal_desk=hiring · occurred_at=2026-06-05T22:34:40.602+00:00 · url=https://www.metacareers.com/jobs/software-engineer · raw={\"location\":\"Menlo Park, CA\",\"ats\":\"agent\"}"},{"ref":"E44","kind":"event","title":"Product Manager","date":"2026-06-05T22:34:40.602+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/product-manager","signal_url":"https://onlylabs.fyi/signals/2d035c24-ac05-4829-91e4-07a86c6fe2e0","signal_json_url":"https://onlylabs.fyi/signals/2d035c24-ac05-4829-91e4-07a86c6fe2e0/signal.json","text":"job_opened · Product Manager · signal_desk=hiring · occurred_at=2026-06-05T22:34:40.602+00:00 · url=https://www.metacareers.com/jobs/product-manager · data_radar_lanes=Product and customer · data_radar_terms=product · data_radar_reason=Meta AI (Llama) has a job signal matching product and customer. · raw={\"location\":\"San Francisco, CA\",\"ats\":\"agent\"}"},{"ref":"E45","kind":"event","title":"Data Scientist, Analytics","date":"2026-06-05T22:31:52.342+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/data-scientist-analytics-new-york","signal_url":"https://onlylabs.fyi/signals/935906ff-27b6-45fd-a23f-2dec2f197b5c","signal_json_url":"https://onlylabs.fyi/signals/935906ff-27b6-45fd-a23f-2dec2f197b5c/signal.json","text":"job_opened · Data Scientist, Analytics · signal_desk=hiring · occurred_at=2026-06-05T22:31:52.342+00:00 · url=https://www.metacareers.com/jobs/data-scientist-analytics-new-york · data_radar_lanes=Data demand · data_radar_terms=data · data_radar_reason=Meta AI (Llama) has a job signal matching data demand. · raw={\"location\":\"New York, NY\",\"ats\":\"agent\"}"},{"ref":"E46","kind":"event","title":"Research Scientist, AI","date":"2026-06-05T22:31:52.342+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/research-scientist-ai-palo-alto","signal_url":"https://onlylabs.fyi/signals/fe2a2461-4915-4592-a86b-ef6cbaa15e51","signal_json_url":"https://onlylabs.fyi/signals/fe2a2461-4915-4592-a86b-ef6cbaa15e51/signal.json","text":"job_opened · Research Scientist, AI · signal_desk=hiring · occurred_at=2026-06-05T22:31:52.342+00:00 · url=https://www.metacareers.com/jobs/research-scientist-ai-palo-alto · raw={\"location\":\"Palo Alto, CA\",\"ats\":\"agent\"}"},{"ref":"E47","kind":"event","title":"Data Scientist, Analytics","date":"2026-06-05T21:53:17.72+00:00","date_source":"source","source_url":"https://www.metacareers.com/jobs/data-scientist-analytics-seattle","signal_url":"https://onlylabs.fyi/signals/814ced71-9172-456e-ad2e-edf7e0879297","signal_json_url":"https://onlylabs.fyi/signals/814ced71-9172-456e-ad2e-edf7e0879297/signal.json","text":"job_opened · Data Scientist, Analytics · signal_desk=hiring · occurred_at=2026-06-05T21:53:17.72+00:00 · url=https://www.metacareers.com/jobs/data-scientist-analytics-seattle · data_radar_lanes=Data demand · data_radar_terms=data · data_radar_reason=Meta AI (Llama) has a job signal matching data demand. · raw={\"location\":\"Seattle, WA\",\"ats\":\"agent\"}"},{"ref":"E48","kind":"event","title":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-Original","date":"2025-04-04T08:02:25+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-Original","signal_url":"https://onlylabs.fyi/signals/f6c9992d-41e0-4f61-a843-2d226e86269a","signal_json_url":"https://onlylabs.fyi/signals/f6c9992d-41e0-4f61-a843-2d226e86269a/signal.json","text":"model_released · meta-llama/Llama-4-Maverick-17B-128E-Instruct-Original · signal_desk=releases · occurred_at=2025-04-04T08:02:25+00:00 · url=https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-Original · hf_downloads=9 · hf_likes=40 · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E49","kind":"event","title":"meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8","date":"2024-10-23T21:39:25+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8","signal_url":"https://onlylabs.fyi/signals/40f10f0e-9f77-4bee-9e1b-3a74a51f1c45","signal_json_url":"https://onlylabs.fyi/signals/40f10f0e-9f77-4bee-9e1b-3a74a51f1c45/signal.json","text":"model_released · meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 · signal_desk=releases · occurred_at=2024-10-23T21:39:25+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 · hf_downloads=75 · hf_likes=39 · pipeline=text-generation · license=llama3.2 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E50","kind":"event","title":"meta-llama/llama-models","date":"2024-06-27T22:14:09+00:00","date_source":"source","source_url":"https://github.com/meta-llama/llama-models","signal_url":"https://onlylabs.fyi/signals/57becf89-298e-4dff-9357-1d7df42851d9","signal_json_url":"https://onlylabs.fyi/signals/57becf89-298e-4dff-9357-1d7df42851d9/signal.json","text":"repo_new · meta-llama/llama-models · signal_desk=repos · occurred_at=2024-06-27T22:14:09+00:00 · url=https://github.com/meta-llama/llama-models · stars=7625 · raw={\"repo\":\"meta-llama/llama-models\",\"description\":\"Utilities intended for use with Llama models.\",\"language\":\"Python\"}"},{"ref":"E51","kind":"event","title":"meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8","date":"2024-10-23T21:30:23+00:00","date_source":"source","source_url":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8","signal_url":"https://onlylabs.fyi/signals/8ba72415-6aec-4750-b63d-f13e4e01fd17","signal_json_url":"https://onlylabs.fyi/signals/8ba72415-6aec-4750-b63d-f13e4e01fd17/signal.json","text":"model_released · meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8 · signal_desk=releases · occurred_at=2024-10-23T21:30:23+00:00 · url=https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8 · hf_downloads=70 · hf_likes=38 · pipeline=text-generation · license=llama3.2 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E52","kind":"event","title":"Meta’s Infrastructure Evolution and the Advent of AI","date":"2025-09-29T13:00:15+00:00","date_source":"rss.item_date","source_url":"https://engineering.fb.com/2025/09/29/data-infrastructure/metas-infrastructure-evolution-and-the-advent-of-ai/","signal_url":"https://onlylabs.fyi/signals/d6517320-3cb4-48f7-b9c8-b34794e691ab","signal_json_url":"https://onlylabs.fyi/signals/d6517320-3cb4-48f7-b9c8-b34794e691ab/signal.json","text":"post_published · Meta’s Infrastructure Evolution and the Advent of AI · signal_desk=talking · occurred_at=2025-09-29T13:00:15+00:00 · url=https://engineering.fb.com/2025/09/29/data-infrastructure/metas-infrastructure-evolution-and-the-advent-of-ai/ · hn=4 points/0 comments · data_radar_lanes=Infrastructure, Product and customer · data_radar_terms=infra, infrastructure, product · data_radar_reason=Meta AI (Llama) has a writing signal matching infrastructure, product and customer. · raw={\"excerpt\":\"Over the past 21 years, Meta has grown exponentially from a small social network connecting a few thousand people in a handful of universities in the U.S. into several apps and novel hardware products that serve over 3.4 billion people throughout the world. Our infrastructure has evolved significantly over the years, growing from a [...]\\nRead More...\\nThe post Meta’s Infrastructure Evolution and the Advent of AI appeared first on Engineering at Meta.\"}"},{"ref":"E53","kind":"event","title":"LLMs Are the Key to Mutation Testing and Better Compliance","date":"2025-09-30T16:00:08+00:00","date_source":"rss.item_date","source_url":"https://engineering.fb.com/2025/09/30/security/llms-are-the-key-to-mutation-testing-and-better-compliance/","signal_url":"https://onlylabs.fyi/signals/cde1856f-b7b1-418c-9fe8-b35b972c3db3","signal_json_url":"https://onlylabs.fyi/signals/cde1856f-b7b1-418c-9fe8-b35b972c3db3/signal.json","text":"post_published · LLMs Are the Key to Mutation Testing and Better Compliance · signal_desk=talking · occurred_at=2025-09-30T16:00:08+00:00 · url=https://engineering.fb.com/2025/09/30/security/llms-are-the-key-to-mutation-testing-and-better-compliance/ · hn=2 points/1 comments · data_radar_lanes=Data demand, Evals and quality, Safety and policy, Product and customer · data_radar_terms=rag, testing, compliance, product · data_radar_reason=Meta AI (Llama) has a writing signal matching data demand, evals and quality, safety and policy, product and customer. · raw={\"excerpt\":\"Following our keynote presentations at FSE 2025 and Eurostar 2025, we’re delving further into the development of Meta’s Automated Compliance Hardening (ACH) tool, an LLM-based tool for software testing that is automating aspects of compliance adherence at Meta, while accelerating developer and product velocity. By leveraging LLMs we’ve been able to overcome the barriers that [...]\\nRead More...\\nThe post LLMs Are the Key to Mutation Testing and Better Compliance appeared first on Engineering at Meta.\"}"},{"ref":"E54","kind":"event","title":"RCCLX: Innovating GPU Communications on AMD Platforms","date":"2026-02-24T21:30:54+00:00","date_source":"rss.item_date","source_url":"https://engineering.fb.com/2026/02/24/data-center-engineering/rrcclx-innovating-gpu-communications-amd-platforms-meta/","signal_url":"https://onlylabs.fyi/signals/8ea9b30b-0fa3-41a8-adc4-940223f4b9b8","signal_json_url":"https://onlylabs.fyi/signals/8ea9b30b-0fa3-41a8-adc4-940223f4b9b8/signal.json","text":"post_published · RCCLX: Innovating GPU Communications on AMD Platforms · signal_desk=talking · occurred_at=2026-02-24T21:30:54+00:00 · url=https://engineering.fb.com/2026/02/24/data-center-engineering/rrcclx-innovating-gpu-communications-amd-platforms-meta/ · data_radar_lanes=Infrastructure · data_radar_terms=platform, gpu · data_radar_reason=Meta AI (Llama) has a writing signal matching infrastructure. · raw={\"excerpt\":\"We are open-sourcing the initial version of RCCLX – an enhanced version of RCCL that we developed and tested on Meta’s internal workloads. RCCLX is fully integrated with Torchcomms and aims to empower researchers and developers to accelerate innovation, regardless of their chosen backend. Communication patterns for AI models are constantly evolving, as are hardware [...]\\nRead More...\\nThe post RCCLX: Innovating GPU Communications on AMD Platforms appeared first on Engineering at Meta.\"}"},{"ref":"E55","kind":"event","title":"Scaling LLM Inference: Innovations in Tensor Parallelism, Context Parallelism, and Expert Parallelism","date":"2025-10-17T16:00:50+00:00","date_source":"rss.item_date","source_url":"https://engineering.fb.com/2025/10/17/ai-research/scaling-llm-inference-innovations-tensor-parallelism-context-parallelism-expert-parallelism/","signal_url":"https://onlylabs.fyi/signals/b6755b1b-e977-458b-b437-a3ee9c5f380b","signal_json_url":"https://onlylabs.fyi/signals/b6755b1b-e977-458b-b437-a3ee9c5f380b/signal.json","text":"post_published · Scaling LLM Inference: Innovations in Tensor Parallelism, Context Parallelism, and Expert Parallelism · signal_desk=talking · occurred_at=2025-10-17T16:00:50+00:00 · url=https://engineering.fb.com/2025/10/17/ai-research/scaling-llm-inference-innovations-tensor-parallelism-context-parallelism-expert-parallelism/ · data_radar_lanes=Infrastructure · data_radar_terms=systems, inference, scaling · data_radar_reason=Meta AI (Llama) has a writing signal matching infrastructure. · raw={\"excerpt\":\"At Meta, we are constantly pushing the boundaries of LLM inference systems to power applications such as the Meta AI App. We’re sharing how we developed and implemented advanced parallelism techniques to optimize key performance metrics related to resource efficiency, throughput, and latency. The rapid evolution of large language models (LLMs) has ushered in a [...]\\nRead More...\\nThe post Scaling LLM Inference: Innovations in Tensor Parallelism, Context Parallelism, and Expert Parallelism appeared first on Engineering at Meta.\"}"},{"ref":"E56","kind":"event","title":"Meta 3D AssetGen: Generating 3D Worlds With AI","date":"2025-09-29T14:00:42+00:00","date_source":"rss.item_date","source_url":"https://engineering.fb.com/2025/09/29/virtual-reality/assetgen-generating-3d-worlds-with-ai/","signal_url":"https://onlylabs.fyi/signals/b9459af8-d126-4d41-8383-2fa2d36c6509","signal_json_url":"https://onlylabs.fyi/signals/b9459af8-d126-4d41-8383-2fa2d36c6509/signal.json","text":"post_published · Meta 3D AssetGen: Generating 3D Worlds With AI · signal_desk=talking · occurred_at=2025-09-29T14:00:42+00:00 · url=https://engineering.fb.com/2025/09/29/virtual-reality/assetgen-generating-3d-worlds-with-ai/ · raw={\"excerpt\":\"Imagine being able to use AI to create 3D virtual worlds using prompts as easily as you can generate images. The intersection of AI and VR was one of the biggest topics at Meta Connect this year. In his keynote, Mark Zuckerberg shared his vision of a future where anyone can create virtual worlds using [...]\\nRead More...\\nThe post Meta 3D AssetGen: Generating 3D Worlds With AI appeared first on Engineering at Meta.\"}"},{"ref":"E57","kind":"event","title":"Diff Risk Score: AI-driven risk-aware software development","date":"2025-08-06T17:50:51+00:00","date_source":"rss.item_date","source_url":"https://engineering.fb.com/2025/08/06/developer-tools/diff-risk-score-drs-ai-risk-aware-software-development-meta/","signal_url":"https://onlylabs.fyi/signals/dfdd2704-0f54-494d-b8da-34168e1a9345","signal_json_url":"https://onlylabs.fyi/signals/dfdd2704-0f54-494d-b8da-34168e1a9345/signal.json","text":"post_published · Diff Risk Score: AI-driven risk-aware software development · signal_desk=talking · occurred_at=2025-08-06T17:50:51+00:00 · url=https://engineering.fb.com/2025/08/06/developer-tools/diff-risk-score-drs-ai-risk-aware-software-development-meta/ · data_radar_lanes=Data demand, Evals and quality, Safety and policy, Product and customer · data_radar_terms=data, eval, risk, product · data_radar_reason=Meta AI (Llama) has a writing signal matching data demand, evals and quality, safety and policy, product and customer. · raw={\"excerpt\":\"The state of the research Diff Risk Score (DRS) is an AI-powered technology built at Meta that predicts the likelihood of a code change causing a production incident, also known as a SEV. Built on a fine-tuned Llama LLM, DRS evaluates code changes and metadata to produce a risk score and highlight potentially risky code [...]\\nRead More...\\nThe post Diff Risk Score: AI-driven risk-aware software development appeared first on Engineering at Meta.\"}"},{"ref":"E58","kind":"event","title":"Building a human-computer interface for everyone","date":"2025-08-04T14:00:25+00:00","date_source":"rss.item_date","source_url":"https://engineering.fb.com/2025/08/04/virtual-reality/building-a-human-computer-interface-for-everyone-meta-tech-podcast/","signal_url":"https://onlylabs.fyi/signals/7d256246-f1de-45ac-8d5a-1b043bbf5390","signal_json_url":"https://onlylabs.fyi/signals/7d256246-f1de-45ac-8d5a-1b043bbf5390/signal.json","text":"post_published · Building a human-computer interface for everyone · signal_desk=talking · occurred_at=2025-08-04T14:00:25+00:00 · url=https://engineering.fb.com/2025/08/04/virtual-reality/building-a-human-computer-interface-for-everyone-meta-tech-podcast/ · raw={\"excerpt\":\"What if you could control any device using only subtle hand movements? New research from Meta’s Reality Labs is pointing even more firmly toward wrist-worn devices using surface electromyography (sEMG) becoming the future of human-computer interaction. But how do you develop a wrist-worn input device that works for everyone? Generalization has been one of the [...]\\nRead More...\\nThe post Building a human-computer interface for everyone appeared first on Engineering at Meta.\"}"},{"ref":"E59","kind":"event","title":"Using AI to make lower-carbon, faster-curing concrete","date":"2025-07-16T12:00:16+00:00","date_source":"rss.item_date","source_url":"https://engineering.fb.com/2025/07/16/data-center-engineering/ai-make-lower-carbon-faster-curing-concrete/","signal_url":"https://onlylabs.fyi/signals/50e33c16-2532-4269-888d-261b50cab19a","signal_json_url":"https://onlylabs.fyi/signals/50e33c16-2532-4269-888d-261b50cab19a/signal.json","text":"post_published · Using AI to make lower-carbon, faster-curing concrete · signal_desk=talking · occurred_at=2025-07-16T12:00:16+00:00 · url=https://engineering.fb.com/2025/07/16/data-center-engineering/ai-make-lower-carbon-faster-curing-concrete/ · data_radar_lanes=Data demand · data_radar_terms=rag · data_radar_reason=Meta AI (Llama) has a writing signal matching data demand. · raw={\"excerpt\":\"Meta has developed an open-source AI tool to design concrete mixes that are stronger, more sustainable, and ready to build with faster—speeding up construction while reducing environmental impact. The AI tool leverages Bayesian optimization, powered by Meta’s BoTorch and Ax frameworks, and was developed with Amrize and the University of Illinois Urbana-Champaign (U of I) [...]\\nRead More...\\nThe post Using AI to make lower-carbon, faster-curing concrete appeared first on Engineering at Meta.\"}"},{"ref":"E60","kind":"event","title":"Accelerating GPU indexes in Faiss with NVIDIA cuVS","date":"2025-05-08T17:00:22+00:00","date_source":"rss.item_date","source_url":"https://engineering.fb.com/2025/05/08/data-infrastructure/accelerating-gpu-indexes-in-faiss-with-nvidia-cuvs/","signal_url":"https://onlylabs.fyi/signals/9bdc08dc-d45d-4ca8-b426-42583f79c6a1","signal_json_url":"https://onlylabs.fyi/signals/9bdc08dc-d45d-4ca8-b426-42583f79c6a1/signal.json","text":"post_published · Accelerating GPU indexes in Faiss with NVIDIA cuVS · signal_desk=talking · occurred_at=2025-05-08T17:00:22+00:00 · url=https://engineering.fb.com/2025/05/08/data-infrastructure/accelerating-gpu-indexes-in-faiss-with-nvidia-cuvs/ · data_radar_lanes=Infrastructure · data_radar_terms=gpu · data_radar_reason=Meta AI (Llama) has a writing signal matching infrastructure. · raw={\"excerpt\":\"Meta and NVIDIA collaborated to accelerate vector search on GPUs by integrating NVIDIA cuVS into Faiss v1.10, Meta’s open source library for similarity search. This new implementation of cuVS will be more performant than classic GPU-accelerated search in some areas. For inverted file (IVF) indexing, NVIDIA cuVS outperforms classical GPU-accelerated IVF build times by up [...]\\nRead More...\\nThe post Accelerating GPU indexes in Faiss with NVIDIA cuVS appeared first on Engineering at Meta.\"}"}]}