跳到正文
    Ertas
    MedErtas

    MedErtas

    面向医疗 AI 的开放模型。

    MedErtas 是面向医疗 AI 公司的开放权重语言模型系列,专为快速、低成本的推理服务打造。

    ~8x

    比基线更快。

    +25%

    准确率高于 MedGemma 27B。

    $0.10 起

    每百万输入 token。

    推出
    MedErtas v0.1。

    31B

    MedErtas-v0.1-31B-LS

    基于 Gemma 4 31B 构建

    适合

    • 医学知识与编码
    • 答案核查
    • 识别无法回答的问题
    输出速度
    189 tokens/s
    权重
    24.2 GB,NVFP4
    草稿模型
    Perigee
    许可证
    Apache-2.0
    27B

    MedErtas-v0.1-27B-LS

    基于 Qwen3.8-27B 构建

    适合

    • 临床计算(有无工具均可)
    • 长病历、短回答
    输出速度
    207 tokens/s
    权重
    22 GB,NVFP4
    草稿模型
    Perigee
    许可证
    Apache-2.0

    详细对比

    哪项工作该用哪个模型。按任务列出准确率(百分比)。“领先”列比较两个 MedErtas 模型,其后列出 MedGemma 27B 作为参考。
    任务31B LS27B LS领先MedGemma 27B参考
    临床计算MedCalc-Bench 1.263.977.327B LS48.6
    工具辅助计算MedCalc with tools61.176.327B LS无
    医学知识MedQA93.086.731B LS87.4
    无法回答的问题MetaMedQA70.465.431B LS36.2
    医学编码MedConceptsQA,中等和困难难度的均值69.863.231B LS46.4
    答案核查MedHallu,3 个难度的均值76.772.331B LS64.7
    长病历LongHealth,2 项任务的均值90.089.0均可27B 处理长输入的成本更低81.5

    潜在应用场景*

    开发者可以让 MedErtas 适配临床工作流,并在智能体系统中以私有方式运行。

    阅读预期用途与局限

    看模型
    如何工作。

    录制示例保留英文原文,即模型运行时使用的语言。

    临床计算

    病历应用 · 入院记录
    入院记录

    An 87-year-old man was admitted to our hospital for anorexia for several days, high-grade fever from the previous day, and liver dysfunction. Of note, he had a history of hypertension, diabetes mellitus (DM), and angina. Physical examination findings included: clear consciousness; height, 163 cm; weight, 48 kg; blood pressure, 66/40 mmHg; heart rate, 75/min; respiratory rate, 22/min; oxygen saturation of peripheral artery, 96%; and body temperature, 38.1 °C. He had no surface lymphadenopathy. Laboratory findings included: white blood cell (WBC) count, 4.2 × 109/L; hemoglobin, 9.6 g/dL; platelet count, 106 × 109/L; lactate dehydrogenase (LDH), 1662 IU/L; aspartate aminotransferase (AST), 6562 IU/L; alanine aminotransferase (ALT), 1407 IU/L; alkaline phosphatase (ALP), 509 IU/L; γ-glutamyl transpeptidase (γ-GTP), 130 IU/L; total bilirubin, 2.7 mg/dL; prothrombin time (PT), 20.3 s; international normalized ratio (INR), 1.73; blood urea nitrogen (BUN), 34.4 mg/dL; and creatinine, 1.4 mg/dL. Serologic tests were all negative for hepatitis A, B, C, and E. Computed tomography (CT) performed at admission revealed no distinct nodules or masses in the liver, but mild splenomegaly, multiple hypodense splenic lesions, and para-aortic lymph node swelling (Fig. a–c). Antibiotics were administered intravenously for suspected acute cholangitis and sepsis, but the fever persisted. Abdominal ultrasonography (US) and magnetic resonance imaging (MRI) performed 2 days later newly depicted gallbladder wall thickening and ascites (Figs. , ). On the same night, the patient presented with grade II hepatic encephalopathy, with blood tests showing a decrease in platelet count and worsening liver function suggestive of “acute type” ALF with hepatic coma and disseminated intravascular coagulation (DIC). While consideration was being given to treating acute liver failure, the patient suddenly developed ventricular fibrillation and died despite immediate resuscitation measures on day 3 of hospitalization. Given the rapid clinical course, an autopsy was performed in this patient with suspected ALF likely due to drug-induced liver injury, autoimmune hepatitis, hepatitis of indeterminate etiology, circulatory disturbance, metabolic disease, or malignant cells including malignant lymphoma. This led to the patient being diagnosed with malignant, diffuse large B-cell lymphoma, characterized by multiple lymph-node, as well as multi-organ (i.e., spleen, liver, lung, and prostate) involvement: (1) general swelling of lymph nodes in the para-abdominal aorta (Fig. a), peripancreatic, peribronchial, pulmonary hilar, subclavicular regions, as well as in the pelvis, especially around the iliac arteries, measuring up to 60 mm in diameter; (2) presence of multiple whitish splenic nodules (Fig. b) with the entire spleen shown to be microscopically infiltrated by tumor cells (Fig. a); (3) irregular geographical morphology of the liver (Fig. c) with the lymphoma cells mainly infiltrating the portal areas (Fig. b); (4) involvement of the right lobe of the lung; (5) involvement of both lobes of the prostate consequent to outer connective tissue involvement (Fig. c). Microscopically, the tumor cells in the lymph nodes were shown to have medium-sized irregular nuclei and small nucleoli with a high nuclear cytoplasmic ratio, thus showing diffuse proliferation characterized by the presence of large numbers of small T-cells (Fig. ). Immunohistochemistry revealed the tumor cells to be positive for CD20 (Fig. a), CD79a (Fig. b), bcl-2 (Fig. c), and MUM1 (Fig. d), but negative for CD3 (Fig. e), CD10, bcl-6, and cyclin D1, with a Ki-67 labeling index (Ki-67 LI) of 16% (Fig. f). The causes of death were thus determined as (1) DIC and (2) ALF associated with diffuse large B-cell lymphoma.

    取自记录
    • 87-year-old
    • weight, 48 kg
    • height, 163 cm
    • creatinine, 1.4 mg/dL
    请求

    What is the patient's Creatinine Clearance using the Cockroft-Gault Equation in terms of mL/min?

    计算助手MedErtas-v0.1-27B-LS
    1. I'll calculate the Creatinine Clearance using the Cockcroft-Gault equation.

      Step 1: Determine BMI and weight category

      Let me extract the values from the patient note: - Age: 87 years - Sex: Male - Height: 163 cm - Weight: 48 kg - Creatinine: 1.4 mg/dL

    2. 调用了 calculator48 / (1.63 * 1.63)= 18.0662
    3. BMI ≈ 18.07, which is underweight (BMI < 18.5).

      Per the instructions: "If the patient is underweight, please set their adjusted body weight to their actual body weight."

      So adjusted body weight = 48 kg (actual weight).

      Step 2: Apply Cockcroft-Gault equation for males:

      CrCl = [(140 − age) × weight] / (72 × serum creatinine)

    4. 调用了 calculator((140 - 87) * 48) / (72 * 1.4)= 25.2381
    5. Calculation: - (140 − 87) = 53 - 53 × 48 = 2544 - 72 × 1.4 = 100.8 - 2544 / 100.8 ≈ 25.24 mL/min

    肌酐清除率25.24mL/min
    2 次工具调用360 个输出 token
    原始提示词和完整录制过程
    模型输入
    You are a helpful assistant. Your task is to read a patient note and compute a medical value based on the following question. You have access to a calculator tool and a python code execution tool. Use them to do any math based on values in the patient note. If using the python tool, make sure the code returns or prints all of its outputs. If there are any errors with compiling or running your script, you may need to re-write your code to obtain the output. Note that all of the necessary information is provided in the patient note and you should not need to prompt the user for any information. When you are finished with all computations, please write your final answer value without any units, using the following formats inside the indicated answer tag: - Decimal Answer Format: 17.29 - Score-Based Answer Format: 5 - Estimated Date Answer Format: 5/21/2021 - Estimated Age Answer Format: (4 weeks, 3 days) Patient Note: An 87-year-old man was admitted to our hospital for anorexia for several days, high-grade fever from the previous day, and liver dysfunction. Of note, he had a history of hypertension, diabetes mellitus (DM), and angina. Physical examination findings included: clear consciousness; height, 163 cm; weight, 48 kg; blood pressure, 66/40 mmHg; heart rate, 75/min; respiratory rate, 22/min; oxygen saturation of peripheral artery, 96%; and body temperature, 38.1 °C. He had no surface lymphadenopathy. Laboratory findings included: white blood cell (WBC) count, 4.2 × 109/L; hemoglobin, 9.6 g/dL; platelet count, 106 × 109/L; lactate dehydrogenase (LDH), 1662 IU/L; aspartate aminotransferase (AST), 6562 IU/L; alanine aminotransferase (ALT), 1407 IU/L; alkaline phosphatase (ALP), 509 IU/L; γ-glutamyl transpeptidase (γ-GTP), 130 IU/L; total bilirubin, 2.7 mg/dL; prothrombin time (PT), 20.3 s; international normalized ratio (INR), 1.73; blood urea nitrogen (BUN), 34.4 mg/dL; and creatinine, 1.4 mg/dL. Serologic tests were all negative for hepatitis A, B, C, and E. Computed tomography (CT) performed at admission revealed no distinct nodules or masses in the liver, but mild splenomegaly, multiple hypodense splenic lesions, and para-aortic lymph node swelling (Fig. a–c). Antibiotics were administered intravenously for suspected acute cholangitis and sepsis, but the fever persisted. Abdominal ultrasonography (US) and magnetic resonance imaging (MRI) performed 2 days later newly depicted gallbladder wall thickening and ascites (Figs. , ). On the same night, the patient presented with grade II hepatic encephalopathy, with blood tests showing a decrease in platelet count and worsening liver function suggestive of “acute type” ALF with hepatic coma and disseminated intravascular coagulation (DIC). While consideration was being given to treating acute liver failure, the patient suddenly developed ventricular fibrillation and died despite immediate resuscitation measures on day 3 of hospitalization. Given the rapid clinical course, an autopsy was performed in this patient with suspected ALF likely due to drug-induced liver injury, autoimmune hepatitis, hepatitis of indeterminate etiology, circulatory disturbance, metabolic disease, or malignant cells including malignant lymphoma. This led to the patient being diagnosed with malignant, diffuse large B-cell lymphoma, characterized by multiple lymph-node, as well as multi-organ (i.e., spleen, liver, lung, and prostate) involvement: (1) general swelling of lymph nodes in the para-abdominal aorta (Fig. a), peripancreatic, peribronchial, pulmonary hilar, subclavicular regions, as well as in the pelvis, especially around the iliac arteries, measuring up to 60 mm in diameter; (2) presence of multiple whitish splenic nodules (Fig. b) with the entire spleen shown to be microscopically infiltrated by tumor cells (Fig. a); (3) irregular geographical morphology of the liver (Fig. c) with the lymphoma cells mainly infiltrating the portal areas (Fig. b); (4) involvement of the right lobe of the lung; (5) involvement of both lobes of the prostate consequent to outer connective tissue involvement (Fig. c). Microscopically, the tumor cells in the lymph nodes were shown to have medium-sized irregular nuclei and small nucleoli with a high nuclear cytoplasmic ratio, thus showing diffuse proliferation characterized by the presence of large numbers of small T-cells (Fig. ). Immunohistochemistry revealed the tumor cells to be positive for CD20 (Fig. a), CD79a (Fig. b), bcl-2 (Fig. c), and MUM1 (Fig. d), but negative for CD3 (Fig. e), CD10, bcl-6, and cyclin D1, with a Ki-67 labeling index (Ki-67 LI) of 16% (Fig. f). The causes of death were thus determined as (1) DIC and (2) ALF associated with diffuse large B-cell lymphoma. Question: What is the patient's Creatinine Clearance using the Cockroft-Gault Equation in terms of mL/min? You should use the patient's adjusted body weight in kg instead of the patient's actual body weight if the patient is overweight or obese based on their BMI. If the patient's BMI's normal, set their adjusted body weight to the minimum of the ideal body and actual weight. If the patient is underweight, please set their adjusted body weight to their actual body weight. You should use the patient's medical values and health status when they were first admitted to the hospital prior to any treatment.
    录制的模型输出 · MedErtas-v0.1-27B-LS
    I'll calculate the Creatinine Clearance using the Cockcroft-Gault equation. **Step 1: Determine BMI and weight category** Let me extract the values from the patient note: - Age: 87 years - Sex: Male - Height: 163 cm - Weight: 48 kg - Creatinine: 1.4 mg/dL
    {"id": "chatcmpl-tool-b4cd295e4a01108c", "name": "calculator", "arguments": "{\"expression\": \"48 / (1.63 * 1.63)\"}"}
    18.06616733787497
    BMI ≈ 18.07, which is **underweight** (BMI < 18.5). Per the instructions: "If the patient is underweight, please set their adjusted body weight to their actual body weight." So adjusted body weight = 48 kg (actual weight). **Step 2: Apply Cockcroft-Gault equation for males:** CrCl = [(140 − age) × weight] / (72 × serum creatinine)
    {"id": "chatcmpl-tool-a00ee6f6473d87f6", "name": "calculator", "arguments": "{\"expression\": \"((140 - 87) * 48) / (72 * 1.4)\"}"}
    25.238095238095237
    **Calculation:** - (140 − 87) = 53 - 53 × 48 = 2544 - 72 × 1.4 = 100.8 - 2544 / 100.8 ≈ **25.24 mL/min** <answer>25.24</answer>
    参考答案25.2381
    此示例的 API 请求

    录制的提示词,temperature 取自评估方案。请确认你的 API 部署所支持的模型标识符和请求选项。你的应用需要自行执行计算器工具循环。

    JSON
    {
      "model": "MedErtas-v0.1-27B-LS",
      "messages": [
        {
          "role": "system",
          "content": "Please reason step by step, use tools as needed, then give your final answer within <answer>...</answer> XML tags."
        },
        {
          "role": "user",
          "content": "You are a helpful assistant. Your task is to read a patient note and compute a medical value based on the following question.\nYou have access to a calculator tool and a python code execution tool. Use them to do any math based on values in the patient note. If using the python tool, make sure the code returns or prints all of its outputs. If there are any errors with compiling or running your script, you may need to re-write your code to obtain the output.\nNote that all of the necessary information is provided in the patient note and you should not need to prompt the user for any information.\nWhen you are finished with all computations, please write your final answer value without any units, using the following formats inside the indicated answer tag:\n\n- Decimal Answer Format: 17.29\n- Score-Based Answer Format: 5\n- Estimated Date Answer Format: 5/21/2021\n- Estimated Age Answer Format: (4 weeks, 3 days)\n\nPatient Note:\n\nAn 87-year-old man was admitted to our hospital for anorexia for several days, high-grade fever from the previous day, and liver dysfunction. Of note, he had a history of hypertension, diabetes mellitus (DM), and angina. Physical examination findings included: clear consciousness; height, 163 cm; weight, 48 kg; blood pressure, 66/40 mmHg; heart rate, 75/min; respiratory rate, 22/min; oxygen saturation of peripheral artery, 96%; and body temperature, 38.1 °C. He had no surface lymphadenopathy. Laboratory findings included: white blood cell (WBC) count, 4.2 × 109/L; hemoglobin, 9.6 g/dL; platelet count, 106 × 109/L; lactate dehydrogenase (LDH), 1662 IU/L; aspartate aminotransferase (AST), 6562 IU/L; alanine aminotransferase (ALT), 1407 IU/L; alkaline phosphatase (ALP), 509 IU/L; γ-glutamyl transpeptidase (γ-GTP), 130 IU/L; total bilirubin, 2.7 mg/dL; prothrombin time (PT), 20.3 s; international normalized ratio (INR), 1.73; blood urea nitrogen (BUN), 34.4 mg/dL; and creatinine, 1.4 mg/dL. Serologic tests were all negative for hepatitis A, B, C, and E. Computed tomography (CT) performed at admission revealed no distinct nodules or masses in the liver, but mild splenomegaly, multiple hypodense splenic lesions, and para-aortic lymph node swelling (Fig. a–c). Antibiotics were administered intravenously for suspected acute cholangitis and sepsis, but the fever persisted. Abdominal ultrasonography (US) and magnetic resonance imaging (MRI) performed 2 days later newly depicted gallbladder wall thickening and ascites (Figs. , ). On the same night, the patient presented with grade II hepatic encephalopathy, with blood tests showing a decrease in platelet count and worsening liver function suggestive of “acute type” ALF with hepatic coma and disseminated intravascular coagulation (DIC). While consideration was being given to treating acute liver failure, the patient suddenly developed ventricular fibrillation and died despite immediate resuscitation measures on day 3 of hospitalization.\nGiven the rapid clinical course, an autopsy was performed in this patient with suspected ALF likely due to drug-induced liver injury, autoimmune hepatitis, hepatitis of indeterminate etiology, circulatory disturbance, metabolic disease, or malignant cells including malignant lymphoma. This led to the patient being diagnosed with malignant, diffuse large B-cell lymphoma, characterized by multiple lymph-node, as well as multi-organ (i.e., spleen, liver, lung, and prostate) involvement: (1) general swelling of lymph nodes in the para-abdominal aorta (Fig. a), peripancreatic, peribronchial, pulmonary hilar, subclavicular regions, as well as in the pelvis, especially around the iliac arteries, measuring up to 60 mm in diameter; (2) presence of multiple whitish splenic nodules (Fig. b) with the entire spleen shown to be microscopically infiltrated by tumor cells (Fig. a); (3) irregular geographical morphology of the liver (Fig. c) with the lymphoma cells mainly infiltrating the portal areas (Fig. b); (4) involvement of the right lobe of the lung; (5) involvement of both lobes of the prostate consequent to outer connective tissue involvement (Fig. c). Microscopically, the tumor cells in the lymph nodes were shown to have medium-sized irregular nuclei and small nucleoli with a high nuclear cytoplasmic ratio, thus showing diffuse proliferation characterized by the presence of large numbers of small T-cells (Fig. ). Immunohistochemistry revealed the tumor cells to be positive for CD20 (Fig. a), CD79a (Fig. b), bcl-2 (Fig. c), and MUM1 (Fig. d), but negative for CD3 (Fig. e), CD10, bcl-6, and cyclin D1, with a Ki-67 labeling index (Ki-67 LI) of 16% (Fig. f). The causes of death were thus determined as (1) DIC and (2) ALF associated with diffuse large B-cell lymphoma.\n\nQuestion:\n\nWhat is the patient's Creatinine Clearance using the Cockroft-Gault Equation in terms of mL/min? You should use the patient's adjusted body weight in kg instead of the patient's actual body weight if the patient is overweight or obese based on their BMI. If the patient's BMI's normal, set their adjusted body weight to the minimum of the ideal body and actual weight. If the patient is underweight, please set their adjusted body weight to their actual body weight. You should use the patient's medical values and health status when they were first admitted to the hospital prior to any treatment."
        }
      ],
      "temperature": 1,
      "chat_template_kwargs": {
        "enable_thinking": false
      },
      "tools": [
        {
          "type": "function",
          "function": {
            "name": "calculator",
            "description": "Evaluate a mathematical expression safely.\n\nSupports basic arithmetic (+, -, *, /, %, **), parentheses, and common math functions. Use ^ or ** for exponentiation.\n\nAvailable functions: sqrt, sin, cos, tan, log, log10, exp, abs, round\nAvailable constants: pi, e",
            "parameters": {
              "properties": {
                "expression": {
                  "description": "A mathematical expression to evaluate.",
                  "title": "Expression",
                  "type": "string"
                }
              },
              "required": [
                "expression"
              ],
              "title": "calculator_args",
              "type": "object",
              "additionalProperties": false
            },
            "strict": null
          }
        },
        {
          "type": "function",
          "function": {
            "name": "code_interpreter",
            "description": "Execute Python code in a sandboxed REPL environment. Variables persist across calls.\n\nThis is a restricted environment - file I/O and network access are disabled.\nAllowed imports: math, numpy, scipy. Pre-loaded: numpy (as np), math, scipy. Use print() to display results.",
            "parameters": {
              "properties": {
                "code": {
                  "description": "A block of Python code to execute.",
                  "title": "Code",
                  "type": "string"
                }
              },
              "required": [
                "code"
              ],
              "title": "code_interpreter_args",
              "type": "object",
              "additionalProperties": false
            },
            "strict": null
          }
        }
      ]
    }

    同样的答案,
    闪电般的速度。

    病历应用 · 计算助手

    同一提示词同时发给两个模型。在全精度且不使用草稿模型时,Qwen3.8-27B 生成这段 144 token 的回答需要 5.54 秒,速度为 26 tokens/s。使用 Perigee 草稿模型的 MedErtas-v0.1-27B-LS 需要 0.70 秒,速度为 207 tokens/s。

    Qwen3.8-27BQwen3.8-27B26 tokens/s
    MedErtas-27B-LSMedErtas-27B-LS207 tokens/s

    速度
    从何而来。

    每个 MedErtas v0.1 模型在每一步之后的输出速度(tokens/s)
    MedErtas v0.1 31B LSMedErtas v0.1 27B LS
    基线22.5 tokens/s26 tokens/s
    医疗校准权重51 tokens/s2.3x60 tokens/s2.3x
    推测式草稿模型168 tokens/s3.3x188 tokens/s3.1x
    Perigee 医疗草稿模型189 tokens/s+13%基线的 8.4x207 tokens/s+10%基线的 8x
    在白皮书中查看完整的速度拆解

    无服务器
    推理定价

    每 1M tokenBetaBeta生产级服务即将推出。目前尚不建议用于高强度生产环境。
    无服务器推理定价,每 1M token
    模型输入缓存读取输出
    MedErtas-v0.1-31B-LS$0.20$0.05$0.60
    MedErtas-v0.1-27B-LS$0.10$0.05$1.00

    MedErtas 常见问题

    什么是 MedErtas?

    MedErtas 是 Ertas AI 推出的开放权重医疗语言模型系列。v0.1 版本基于 Gemma 4 31B 和 Qwen3.8-27B 构建,把领域感知的 4 位量化与我们的医疗草稿模型 Perigee 结合起来,让推理服务更快。

    我该用哪个 MedErtas 模型?

    如果是临床计算或输入量大的长病历应用,先从 MedErtas-v0.1-27B-LS 开始。如果是医学知识、编码知识和答案核查,先从 MedErtas-v0.1-31B-LS 开始。27B 的输入价格更低,31B 的输出价格更低。请在你自己的工作负载上评估准确率、延迟和总 token 用量。

    MedErtas 是开源的吗?

    模型权重和 Perigee 医疗草稿模型均以 Apache-2.0 许可证发布在 Hugging Face 上。你可以下载它们并自行部署。托管 API 是使用这些模型的一种可选方式。

    MedErtas 与 MedGemma 有何不同?

    Medmarks 排行榜与我们的测试共同覆盖 11 项医疗基准测试。在这些测试上,MedErtas 31B 和 27B 的平均得分分别为 79.6 和 77.1,比 MedGemma 27B 在 2026年10月26日排行榜快照中的 63.6 分别高出 16.0 分和 13.5 分。这些是基准测试结果,并非临床适用性的证据。MedErtas v0.1 仅支持文本,为快速推理服务而打造,采用领域感知量化和 Perigee 医疗草稿模型;MedGemma 还支持医学影像理解。MedErtas 使用 Apache-2.0 许可证,MedGemma 使用 Health AI Developer Foundations 条款。Ertas 提供按 token 计价的 Beta 版 API,Google 的 Vertex AI 部署则使用专用端点。请根据你的部署方式查询服务商的当前定价。

    可以在本地部署 MedErtas 吗?

    可以。权重和 Perigee 草稿模型都可以下载。权重使用 NVFP4,可在 NVIDIA Blackwell GPU 上运行。31B 模型的权重为 24.2 GB,另加 1.0 GB 的 Perigee 草稿模型;27B 模型的权重为 22 GB。运行时内存取决于你的配置。想在自己的云、本地或气隙环境中部署,可以和我们聊聊。

    4 位量化对医疗模型安全吗?

    每个医疗模型,包括全精度模型,在投入生产前都应纳入经过精心设计和审查的系统。MedErtas 的目标是在医疗能力上与全精度基础模型保持一致,同时让模型推理更快、成本更低,每次发布都会公布我们测试的每个数据集与全精度的对比。其他发布者的压缩版本仍可能在特定医疗任务上损失准确率。在依赖任何模型之前,请在你自己的临床任务上将它与全精度版本对比测试。

    模型名称中的 LS 是什么意思?

    LS 是 Lightweight Study(轻量研究)的缩写,指这一构建配置。LS 版本用领域感知量化压缩权重,并搭配针对该领域训练的草稿模型,模型本身的训练保持不变。后续配置将涵盖用领域数据进行后训练的模型。

    什么是 Perigee?

    Perigee 是 MedErtas 医疗草稿模型的名称。草稿模型是一个小型配套模型,在推测解码中提前提议多个 token;主模型一次性检查这些 token,只保留它自己也会生成的部分,因此回答仍然遵循主模型,而且来得更快。MedErtas-v0.1-31B-LS-Perigee 是 Google 的 Gemma 4 31B 辅助草稿模型,基于医疗回答微调。MedErtas-v0.1-27B-LS-Perigee 是 Red Hat 面向 Qwen3.8-27B 的 DSpark 草稿模型,基于医疗回答进一步训练。两者均以 Apache-2.0 许可证发布在 Hugging Face 上,并通过 vLLM 运行。这个名字来自轨道上距离所环绕天体最近的那个点:草稿模型越贴近主模型,被接受的 token 就越多。

    可以在生产环境中使用 MedErtas API 吗?

    目前还不适合高强度或对稳定性有要求的生产用途。在我们完善生产级服务期间,API 处于 Beta 阶段。如果你想在自己的硬件上运行,权重已发布在 Hugging Face 上;如果你在规划生产规模的用量,可以和我们聊聊。

    MedErtas 版本发布

    预期用途
    与局限

    对于基于医学文本构建医疗健康应用的开发者,MedErtas 是一个起点。每个用例都需要开发者单独进行验证、适配或实质性修改,之后才能依赖该模型。

    MedErtas 模型的输出并非旨在直接为临床诊断、患者管理决策、治疗建议或任何其他直接临床实践提供依据。基准测试结果反映的是模型在我们列明的测试上的基础能力,输出可能不准确。请将每一项输出都视为初步结果:它需要独立核实和临床审查。

    用 MedErtas
    开始构建。

    正在规划生产规模的用量? 与我们聊聊