{
    "componentChunkName": "component---src-templates-note-note-js",
    "path": "/notes/deep-seek-paper",
    "result": {"data":{"mdx":{"body":"var _excluded = [\"components\"];\nfunction _extends() { _extends = Object.assign ? Object.assign.bind() : function (target) { for (var i = 1; i < arguments.length; i++) { var source = arguments[i]; for (var key in source) { if (Object.prototype.hasOwnProperty.call(source, key)) { target[key] = source[key]; } } } return target; }; return _extends.apply(this, arguments); }\nfunction _objectWithoutProperties(source, excluded) { if (source == null) return {}; var target = _objectWithoutPropertiesLoose(source, excluded); var key, i; if (Object.getOwnPropertySymbols) { var sourceSymbolKeys = Object.getOwnPropertySymbols(source); for (i = 0; i < sourceSymbolKeys.length; i++) { key = sourceSymbolKeys[i]; if (excluded.indexOf(key) >= 0) continue; if (!Object.prototype.propertyIsEnumerable.call(source, key)) continue; target[key] = source[key]; } } return target; }\nfunction _objectWithoutPropertiesLoose(source, excluded) { if (source == null) return {}; var target = {}; var sourceKeys = Object.keys(source); var key, i; for (i = 0; i < sourceKeys.length; i++) { key = sourceKeys[i]; if (excluded.indexOf(key) >= 0) continue; target[key] = source[key]; } return target; }\n/* @jsxRuntime classic */\n/* @jsx mdx */\n\nvar _frontmatter = {};\nvar layoutProps = {\n  _frontmatter: _frontmatter\n};\nvar MDXLayout = \"wrapper\";\nreturn function MDXContent(_ref) {\n  var components = _ref.components,\n    props = _objectWithoutProperties(_ref, _excluded);\n  return mdx(MDXLayout, _extends({}, layoutProps, props, {\n    components: components,\n    mdxType: \"MDXLayout\"\n  }), mdx(\"p\", null, mdx(\"a\", {\n    parentName: \"p\",\n    \"href\": \"https://www.youtube.com/watch?v=XMnxKGVnEUc\"\n  }, \"https://www.youtube.com/watch?v=XMnxKGVnEUc\")), mdx(\"p\", null, \"PPO, DPO and ORPO\"), mdx(\"h2\", null, \"From \", mdx(\"a\", {\n    parentName: \"h2\",\n    \"href\": \"https://lifeinthesingularity.com/p/deepseek-proves-ai-comes-for-all\"\n  }, \"https://lifeinthesingularity.com/p/deepseek-proves-ai-comes-for-all\")), mdx(\"ol\", null, mdx(\"li\", {\n    parentName: \"ol\"\n  }, \"Once the reasoning-oriented RL converged, the checkpoint was used to create new SFT data\"), mdx(\"li\", {\n    parentName: \"ol\"\n  }, \"To sum it up neatly \\u2192 the training process of DeepSeek-R1 is a multi-stage process that starts with a pure RL approach to establish reasoning capabilities, then introduces a cold start with high-quality data, followed by further refinement through both RL and SFT, and finally distillation to transfer these reasoning capabilities to smaller models. This combination of techniques resulted in a model that performs comparably to OpenAI-o1-1217 (cutting edge as of this writing) on various reasoning tasks.\"), mdx(\"li\", {\n    parentName: \"ol\"\n  }, \"By combining RL with SFT and distillation, DeepSeek-R1 achieves comparable performance to cutting-edge models like OpenAI's, potentially at a fraction of the training cost. This could democratize access to advanced AI, making it more affordable and accessible for researchers, developers, and smaller organizations.\"), mdx(\"li\", {\n    parentName: \"ol\"\n  })));\n}\n;\nMDXContent.isMDXComponent = true;","inboundReferences":[]}},"pageContext":{"slug":"deep-seek-paper","node":{"childMdx":{"slug":"deep-seek-paper"}}}},
    "staticQueryHashes": []}