{"id":30263,"date":"2025-04-10T19:50:04","date_gmt":"2025-04-10T11:50:04","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=30263"},"modified":"2025-04-10T19:50:04","modified_gmt":"2025-04-10T11:50:04","slug":"deepcoder-14b-preview","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/ja\/deepcoder-14b-preview\/","title":{"rendered":"DeepCoder-14B-Preview\uff1a\u64c5\u957f\u4ee3\u7801\u751f\u6210\u7684\u7684\u5f00\u6e90\u6a21\u578b"},"content":{"rendered":"<p>DeepCoder-14B-Preview \u662f\u7531 Agentica \u56e2\u961f\u5f00\u53d1\u5e76\u5728 Hugging Face \u5e73\u53f0\u53d1\u5e03\u7684\u5f00\u6e90\u4ee3\u7801\u751f\u6210\u6a21\u578b\u3002\u5b83\u57fa\u4e8e DeepSeek-R1-Distilled-Qwen-14B\uff0c\u901a\u8fc7\u5206\u5e03\u5f0f\u5f3a\u5316\u5b66\u4e60\uff08RL\uff09\u6280\u672f\u4f18\u5316\uff0c\u80fd\u5904\u7406\u9ad8\u8fbe 64K <a href=\"https:\/\/www.kdjingpai.com\/pt\/tokenization\/\">token<\/a> \u7684\u8d85\u957f\u4e0a\u4e0b\u6587\u3002\u8fd9\u4e2a\u6a21\u578b\u62e5\u6709 140 \u4ebf\u53c2\u6570\uff0c\u5728 LiveCodeBench v5 \u6d4b\u8bd5\uff082024\u5e748\u67081\u65e5\u81f32025\u5e742\u67081\u65e5\uff09\u4e2d\u83b7\u5f97 60.6% \u7684 Pass@1 \u51c6\u786e\u7387\uff0c\u6bd4\u57fa\u7840\u6a21\u578b\u63d0\u5347\u4e86 8%\uff0c\u6027\u80fd\u63a5\u8fd1 OpenAI \u7684 o3-mini\u3002\u5b83\u5b8c\u5168\u5f00\u6e90\uff0c\u5305\u62ec\u6a21\u578b\u6743\u91cd\u3001\u8bad\u7ec3\u6570\u636e\u548c\u811a\u672c\uff0c\u4efb\u4f55\u4eba\u90fd\u53ef\u4ee5\u514d\u8d39\u4e0b\u8f7d\u4f7f\u7528\u3002DeepCoder \u7684\u76ee\u6807\u662f\u5e2e\u52a9\u5f00\u53d1\u8005\u9ad8\u6548\u7f16\u5199\u590d\u6742\u4ee3\u7801\uff0c\u7279\u522b\u9002\u5408\u7f16\u7a0b\u7ade\u8d5b\u548c\u5927\u578b\u9879\u76ee\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter  wp-image-30264\" title=\"DeepCoder-14B-Preview\uff1a\u64c5\u957f\u4ee3\u7801\u751f\u6210\u7684\u7684\u5f00\u6e90\u6a21\u578b-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/04\/39e819b4fa09ce4.jpg\" alt=\"DeepCoder-14B-Preview\uff1a\u64c5\u957f\u4ee3\u7801\u751f\u6210\u7684\u7684\u5f00\u6e90\u6a21\u578b-1\" width=\"663\" height=\"358\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/04\/39e819b4fa09ce4.jpg 1200w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/04\/39e819b4fa09ce4-768x415.jpg 768w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/04\/39e819b4fa09ce4-18x10.jpg 18w\" sizes=\"auto, (max-width: 663px) 100vw, 663px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li>\u751f\u6210\u957f\u4ee3\u7801\uff1a\u652f\u6301\u6700\u9ad8 64K token \u7684\u4e0a\u4e0b\u6587\uff0c\u80fd\u751f\u6210\u548c\u5904\u7406\u8d85\u957f\u4ee3\u7801\u3002<\/li>\n<li>\u9ad8\u51c6\u786e\u7387\u8f93\u51fa\uff1a\u5728 LiveCodeBench v5 \u4e2d\u8fbe\u5230 60.6% Pass@1\uff0c\u4ee3\u7801\u8d28\u91cf\u53ef\u9760\u3002<\/li>\n<li>\u5f00\u6e90\u53ef\u7528\uff1a\u63d0\u4f9b\u6a21\u578b\u6587\u4ef6\u3001\u6570\u636e\u96c6\u548c\u8bad\u7ec3\u811a\u672c\uff0c\u514d\u8d39\u4e0b\u8f7d\u548c\u81ea\u5b9a\u4e49\u3002<\/li>\n<li>\u652f\u6301\u591a\u79cd\u7f16\u7a0b\u4efb\u52a1\uff1a\u9002\u5408\u7ade\u8d5b\u9898\u76ee\u89e3\u7b54\u3001\u4ee3\u7801\u8c03\u8bd5\u548c\u9879\u76ee\u5f00\u53d1\u3002<\/li>\n<li>\u957f\u4e0a\u4e0b\u6587\u63a8\u7406\uff1a\u901a\u8fc7 GRPO+ \u548c DAPO \u6280\u672f\u4f18\u5316\uff0c\u786e\u4fdd\u957f\u4ee3\u7801\u751f\u6210\u80fd\u529b\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<p>DeepCoder-14B-Preview \u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u5e2e\u52a9\u4f60\u751f\u6210\u4ee3\u7801\u6216\u5904\u7406\u590d\u6742\u7f16\u7a0b\u4efb\u52a1\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u7684\u5b89\u88c5\u548c\u4f7f\u7528\u6307\u5357\u3002<\/p>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<p>\u8981\u5728\u672c\u5730\u4f7f\u7528 DeepCoder-14B-Preview\uff0c\u9700\u8981\u51c6\u5907\u73af\u5883\u5e76\u4e0b\u8f7d\u6a21\u578b\u3002\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<ol>\n<li><strong>\u51c6\u5907\u786c\u4ef6\u548c\u8f6f\u4ef6<\/strong>\n<ul>\n<li>\u9700\u8981\u4e00\u53f0\u5e26 GPU \u7684\u7535\u8111\uff0c\u63a8\u8350 NVIDIA H100 \u6216\u81f3\u5c11 24GB \u663e\u5b58\u7684\u663e\u5361\u3002<\/li>\n<li>\u5b89\u88c5 Python 3.10\uff1a\u8fd0\u884c\u00a0<code>conda create -n deepcoder python=3.10 -y<\/code>\uff0c\u7136\u540e\u6fc0\u6d3b\u73af\u5883\u00a0<code>conda activate deepcoder<\/code>\u3002<\/li>\n<li>\u5b89\u88c5\u4f9d\u8d56\u5e93\uff1a\u8fd0\u884c\u00a0<code>pip install transformers torch huggingface_hub <a href=\"https:\/\/www.kdjingpai.com\/pt\/vllm\/\">vllm<\/a><\/code>\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u4e0b\u8f7d\u6a21\u578b<\/strong>\n<ul>\n<li>\u8bbf\u95ee\u5b98\u65b9\u9875\u9762\uff1ahttps:\/\/huggingface.co\/agentica-org\/DeepCoder-14B-Preview\u3002<\/li>\n<li>\u5728\u201cFiles and versions\u201d\u4e2d\u627e\u5230\u6a21\u578b\u6587\u4ef6\uff08\u5982\u00a0<code>model-00001-of-00012.safetensors<\/code>\uff09\u3002<\/li>\n<li>\u4f7f\u7528\u547d\u4ee4\u4e0b\u8f7d\uff1a\n<pre><code>huggingface-cli download agentica-org\/DeepCoder-14B-Preview --local-dir .\/DeepCoder-14B\r\n<\/code><\/pre>\n<\/li>\n<li>\u4e0b\u8f7d\u540e\uff0c\u6a21\u578b\u6587\u4ef6\u4f1a\u4fdd\u5b58\u5728\u672c\u5730\u00a0<code>.\/DeepCoder-14B<\/code>\u00a0\u6587\u4ef6\u5939\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u52a0\u8f7d\u6a21\u578b<\/strong>\n<ul>\n<li>\u5728 Python \u4e2d\u52a0\u8f7d\u6a21\u578b\uff1a\n<pre><code>from transformers import AutoModelForCausalLM, AutoTokenizer\r\nmodel_path = \".\/DeepCoder-14B\"\r\nmodel = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=\"auto\", device_map=\"auto\")\r\ntokenizer = AutoTokenizer.from_pretrained(model_path)\r\n<\/code><\/pre>\n<\/li>\n<li>\u8fd9\u4f1a\u5c06\u6a21\u578b\u52a0\u8f7d\u5230 GPU \u4e0a\uff0c\u51c6\u5907\u4f7f\u7528\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h3>\u5982\u4f55\u4f7f\u7528\u4e3b\u8981\u529f\u80fd<\/h3>\n<p>DeepCoder \u7684\u6838\u5fc3\u662f\u751f\u6210\u4ee3\u7801\u548c\u5904\u7406\u957f\u4e0a\u4e0b\u6587\u3002\u4ee5\u4e0b\u662f\u64cd\u4f5c\u65b9\u6cd5\uff1a<\/p>\n<h4>\u751f\u6210\u4ee3\u7801<\/h4>\n<ol>\n<li><strong>\u8f93\u5165\u7f16\u7a0b\u9700\u6c42<\/strong>\n<ul>\n<li>\u51c6\u5907\u4e00\u4e2a\u95ee\u9898\uff0c\u6bd4\u5982\u201c\u5199\u4e00\u4e2a Python \u51fd\u6570\uff0c\u627e\u51fa\u6570\u7ec4\u4e2d\u7684\u6700\u5927\u503c\u201d\u3002<\/li>\n<li>\u5c06\u9700\u6c42\u8f6c\u4e3a\u6587\u672c\uff1a\n<pre><code>prompt = \"\u5199\u4e00\u4e2a Python \u51fd\u6570\uff0c\u627e\u51fa\u6570\u7ec4\u4e2d\u7684\u6700\u5927\u503c\"\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u751f\u6210\u4ee3\u7801<\/strong>\n<ul>\n<li>\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u751f\u6210\u7b54\u6848\uff1a\n<pre><code>inputs = tokenizer(prompt, return_tensors=\"pt\").to(model.device)\r\noutputs = model.generate(**inputs, max_new_tokens=512, temperature=0.6, top_p=0.95)\r\nresult = tokenizer.decode(outputs[0], skip_special_tokens=True)\r\nprint(result)\r\n<\/code><\/pre>\n<\/li>\n<li>\u53ef\u80fd\u7684\u8f93\u51fa\uff1a\n<pre><code>def find_max(arr):\r\nif not arr:\r\nreturn None\r\nmax_value = arr[0]\r\nfor num in arr:\r\nif num &gt; max_value:\r\nmax_value = num\r\nreturn max_value\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u4f18\u5316\u751f\u6210<\/strong>\n<ul>\n<li>\u5982\u679c\u9700\u8981\u66f4\u957f\u4ee3\u7801\uff0c\u8c03\u6574\u00a0<code>max_new_tokens<\/code>\u00a0\u4e3a 1024 \u6216\u66f4\u9ad8\u3002<\/li>\n<li>\u8bbe\u7f6e\u00a0<code>max_tokens=64000<\/code>\u00a0\u53ef\u83b7\u5f97\u6700\u4f73\u957f\u4e0a\u4e0b\u6587\u6027\u80fd\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h4>\u5904\u7406\u957f\u4e0a\u4e0b\u6587<\/h4>\n<ol>\n<li><strong>\u8f93\u5165\u957f\u4ee3\u7801<\/strong>\n<ul>\n<li>\u5047\u8bbe\u4f60\u6709\u4e00\u4e2a\u957f\u8fbe 32K token \u7684\u4ee3\u7801\uff0c\u60f3\u8ba9\u6a21\u578b\u7eed\u5199\uff1a\n<pre><code>long_code = \"def process_data(data):\\n    # \u51e0\u5343\u884c\u4ee3\u7801...\\n    return processed_data\"\r\nprompt = long_code + \"\\n\u8bf7\u4e3a\u8fd9\u4e2a\u51fd\u6570\u6dfb\u52a0\u5f02\u5e38\u5904\u7406\"\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u751f\u6210\u7eed\u5199<\/strong>\n<ul>\n<li>\u8f93\u5165\u5e76\u751f\u6210\uff1a\n<pre><code>inputs = tokenizer(prompt, return_tensors=\"pt\").to(model.device)\r\noutputs = model.generate(**inputs, max_new_tokens=512, temperature=0.6, top_p=0.95)\r\nresult = tokenizer.decode(outputs[0], skip_special_tokens=True)\r\nprint(result)\r\n<\/code><\/pre>\n<\/li>\n<li>\u8f93\u51fa\u53ef\u80fd\u662f\uff1a\n<pre><code>def process_data(data):\r\ntry:\r\n# \u51e0\u5343\u884c\u4ee3\u7801...\r\nreturn processed_data\r\nexcept Exception as e:\r\nprint(f\"\u9519\u8bef: {e}\")\r\nreturn None\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u9a8c\u8bc1\u7ed3\u679c<\/strong>\n<ul>\n<li>\u68c0\u67e5\u4ee3\u7801\u662f\u5426\u7b26\u5408\u9700\u6c42\u3002\u5982\u679c\u4e0d\u7406\u60f3\uff0c\u53ef\u4ee5\u66f4\u660e\u786e\u63cf\u8ff0\u9700\u6c42\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h3>\u7279\u8272\u529f\u80fd\u64cd\u4f5c\u6d41\u7a0b<\/h3>\n<p>DeepCoder \u7684\u957f\u4ee3\u7801\u751f\u6210\u80fd\u529b\u662f\u5176\u4eae\u70b9\uff0c\u9002\u5408\u7ade\u8d5b\u548c\u5927\u578b\u9879\u76ee\u3002<\/p>\n<h4>\u89e3\u51b3\u7ade\u8d5b\u9898\u76ee<\/h4>\n<ol>\n<li><strong>\u83b7\u53d6\u9898\u76ee<\/strong>\n<ul>\n<li>\u4ece Codeforces \u627e\u4e00\u4e2a\u9898\u76ee\uff0c\u6bd4\u5982\u201c\u7ed9\u5b9a\u4e00\u4e2a\u6570\u7ec4\uff0c\u8fd4\u56de\u6240\u6709\u53ef\u80fd\u7684\u5b50\u96c6\u201d\u3002<\/li>\n<li>\u8f93\u5165\u9898\u76ee\u63cf\u8ff0\uff1a\n<pre><code>prompt = \"\u7ed9\u5b9a\u4e00\u4e2a\u6570\u7ec4\uff0c\u8fd4\u56de\u6240\u6709\u53ef\u80fd\u7684\u5b50\u96c6\u3002\u4f8b\u5982\uff0c\u8f93\u5165 [1,2,3]\uff0c\u8f93\u51fa [[],[1],[2],[3],[1,2],[1,3],[2,3],[1,2,3]]\"\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u751f\u6210\u4ee3\u7801<\/strong>\n<ul>\n<li>\u8fd0\u884c\u751f\u6210\u547d\u4ee4\uff1a\n<pre><code>inputs = tokenizer(prompt, return_tensors=\"pt\").to(model.device)\r\noutputs = model.generate(**inputs, max_new_tokens=512, temperature=0.6, top_p=0.95)\r\nresult = tokenizer.decode(outputs[0], skip_special_tokens=True)\r\nprint(result)\r\n<\/code><\/pre>\n<\/li>\n<li>\u8f93\u51fa\u53ef\u80fd\u662f\uff1a\n<pre><code>def subsets(nums):\r\nresult = [[]]\r\nfor num in nums:\r\nresult += [curr + [num] for curr in result]\r\nreturn result\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u6d4b\u8bd5\u7ed3\u679c<\/strong>\n<ul>\n<li>\u5728 Python \u4e2d\u8fd0\u884c\u4ee3\u7801\uff0c\u8f93\u5165\u00a0<code>[1,2,3]<\/code>\uff0c\u68c0\u67e5\u8f93\u51fa\u662f\u5426\u6b63\u786e\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h4>\u8c03\u8bd5\u4ee3\u7801<\/h4>\n<ol>\n<li><strong>\u8f93\u5165\u95ee\u9898\u4ee3\u7801<\/strong>\n<ul>\n<li>\u5047\u8bbe\u6709\u4e00\u6bb5\u6709 Bug \u7684\u4ee3\u7801\uff1a\n<pre><code>buggy_code = \"def sum_numbers(n):\\n    total = 0\\n    for i in range(n)\\n        total += i\\n    return total\"\r\nprompt = buggy_code + \"\\n\u8fd9\u6bb5\u4ee3\u7801\u6709\u8bed\u6cd5\u9519\u8bef\uff0c\u8bf7\u4fee\u590d\"\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u751f\u6210\u4fee\u590d\u7248\u672c<\/strong>\n<ul>\n<li>\u8f93\u5165\u5e76\u751f\u6210\uff1a\n<pre><code>inputs = tokenizer(prompt, return_tensors=\"pt\").to(model.device)\r\noutputs = model.generate(**inputs, max_new_tokens=512, temperature=0.6, top_p=0.95)\r\nresult = tokenizer.decode(outputs[0], skip_special_tokens=True)\r\nprint(result)\r\n<\/code><\/pre>\n<\/li>\n<li>\u8f93\u51fa\u53ef\u80fd\u662f\uff1a\n<pre><code>def sum_numbers(n):\r\ntotal = 0\r\nfor i in range(n):\r\ntotal += i\r\nreturn total\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u9a8c\u8bc1\u4fee\u590d<\/strong>\n<ul>\n<li>\u68c0\u67e5\u8bed\u6cd5\u662f\u5426\u6b63\u786e\uff0c\u8fd0\u884c\u4ee3\u7801\u786e\u8ba4\u7ed3\u679c\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h3>\u4f7f\u7528\u5efa\u8bae<\/h3>\n<ul>\n<li>\u4e0d\u8981\u6dfb\u52a0\u7cfb\u7edf\u63d0\u793a\uff0c\u76f4\u63a5\u5728\u7528\u6237\u63d0\u793a\u4e2d\u8bf4\u660e\u9700\u6c42\u3002<\/li>\n<li>\u8bbe\u7f6e\u00a0<code>temperature=0.6<\/code>\u00a0\u548c\u00a0<code>top_p=0.95<\/code>\u00a0\u4ee5\u83b7\u5f97\u6700\u4f73\u7ed3\u679c\u3002<\/li>\n<li>\u5c06\u00a0<code>max_tokens<\/code>\u00a0\u8bbe\u7f6e\u4e3a 64000 \u4ee5\u53d1\u6325\u957f\u4e0a\u4e0b\u6587\u4f18\u52bf\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u5e94\u7528\u573a\u666f<\/h2>\n<ol>\n<li><strong>\u7f16\u7a0b\u7ade\u8d5b<\/strong><br \/>\nDeepCoder \u80fd\u5feb\u901f\u751f\u6210\u7ade\u8d5b\u9898\u76ee\u7b54\u6848\uff0c\u9002\u5408 LiveCodeBench \u6216 Codeforces \u7684\u590d\u6742\u4efb\u52a1\u3002<\/li>\n<li><strong>\u5927\u578b\u9879\u76ee\u5f00\u53d1<\/strong><br \/>\n\u5b83\u53ef\u4ee5\u751f\u6210\u957f\u4ee3\u7801\u6a21\u5757\uff0c\u5e2e\u52a9\u5f00\u53d1\u8005\u5b8c\u6210\u5927\u578b\u9879\u76ee\u3002<\/li>\n<li><strong>\u6559\u80b2\u548c\u5b66\u4e60<\/strong><br \/>\n\u5b66\u751f\u53ef\u4ee5\u7528\u5b83\u751f\u6210\u793a\u4f8b\u4ee3\u7801\uff0c\u5b66\u4e60\u7b97\u6cd5\u6216\u8c03\u8bd5\u4f5c\u4e1a\u3002<\/li>\n<\/ol>\n<p>&nbsp;<\/p>\n<h2>QA<\/h2>\n<ol>\n<li><strong>DeepCoder-14B-Preview \u662f\u514d\u8d39\u7684\u5417\uff1f<\/strong><br \/>\n\u662f\u7684\uff0c\u5b83\u91c7\u7528 MIT \u8bb8\u53ef\uff0c\u5b8c\u5168\u5f00\u6e90\uff0c\u4efb\u4f55\u4eba\u90fd\u53ef\u4ee5\u514d\u8d39\u4f7f\u7528\u3002<\/li>\n<li><strong>\u9700\u8981\u4ec0\u4e48\u786c\u4ef6\u624d\u80fd\u8fd0\u884c\uff1f<\/strong><br \/>\n\u63a8\u8350\u4f7f\u7528\u5e26 GPU \u7684\u7535\u8111\uff0c\u81f3\u5c11 24GB \u663e\u5b58\u3002\u5982\u679c\u7528 CPU\uff0c\u901f\u5ea6\u4f1a\u6162\u5f88\u591a\u3002<\/li>\n<li><strong>\u5b83\u652f\u6301\u54ea\u4e9b\u7f16\u7a0b\u8bed\u8a00\uff1f<\/strong><br \/>\n\u5b83\u4e3b\u8981\u64c5\u957f Python\uff0c\u4f46\u4e5f\u80fd\u751f\u6210 Java\u3001C++ \u7b49\u8bed\u8a00\u7684\u4ee3\u7801\uff0c\u6548\u679c\u53d6\u51b3\u4e8e\u63d0\u793a\u6e05\u6670\u5ea6\u3002<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>DeepCoder-14B-Preview \u662f\u7531 Agentica \u56e2\u961f\u5f00\u53d1\u5e76\u5728 Hugging Face \u5e73\u53f0\u53d1\u5e03\u7684\u5f00\u6e90\u4ee3\u7801\u751f\u6210\u6a21\u578b\u3002\u5b83\u57fa\u4e8e DeepSeek-R1-Distilled-Qwen-14B\uff0c\u901a\u8fc7\u5206\u5e03\u5f0f\u5f3a\u5316\u5b66\u4e60\uff08RL\uff09\u6280\u672f\u4f18\u5316&#8230;<\/p>\n","protected":false},"author":1,"featured_media":62230,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[230,365],"class_list":["post-30263","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","tag-aikaiyuanxiangmu","tag-damoxingweidiao"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/posts\/30263","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/comments?post=30263"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/posts\/30263\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/media\/62230"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/media?parent=30263"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/categories?post=30263"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/tags?post=30263"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}