47:I[603186,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/3d3xbt99nfqun.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"PageMetadata"] 48:I[831915,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/3d3xbt99nfqun.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"SearchResultsImage"] 49:I[66106,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/3d3xbt99nfqun.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/0fpx6rmsgi4um.js"],""] 4a:I[299632,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/3d3xbt99nfqun.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"default"] 4b:I[400402,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/3d3xbt99nfqun.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"EndpointCTA"] 4c:I[331699,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/3d3xbt99nfqun.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"ModelContent"] 51:I[946424,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/3d3xbt99nfqun.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"default"] 44:["$","$L47",null,{"hasPartnerEndpoint":false}] 4d:T478b,# Model Overview ## Description This open Nemotron safety model, *Llama 3.1 NemoGuard Content Safety*, is a content safety model that moderates human-LLM interaction content and classifies user prompts and LLM responses as safe or unsafe. If the content is unsafe, the model additionally returns a response with a list of categories that the content violates. The base large language model (LLM) is the multilingual [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) model from Meta. NVIDIA’s optimized release is LoRa-tuned on approved datasets and better conforms NVIDIA’s content safety risk taxonomy and other safety risks in human-LLM interactions. [Version 3](https://build.nvidia.com/nvidia/llama-3_1-nemotron-safety-guard-8b-v3) of this model includes multilingual support. The model can be prompted using an instruction and a taxonomy of unsafe risks to be categorized. The instruction format for prompt moderation is shown below under input and output examples. This model is supported in the open NVIDIA NeMo Guardrails library, designed to simplify scalable AI guardrail orchestration for safeguarding agentic AI applications. ### License/Terms of Use: Governing NVIDIA Model Hosting Terms (Cloud API) GOVERNING TERMS: This trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Community License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). Additional Information: [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/). Built with Llama. Governing NVIDIA Download Terms & Third-Party Component Attribution Terms (Hugging Face LORA weights) GOVERNING TERMS: Use of this model is governed by the [NVIDIA Open Model License Agreement](https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf). Additional Information: [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/). Built with Llama. GOVERNING TERMS: Use of the NIM container is governed by the [NVIDIA Software License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/) and the [Product-Specific Terms for NVIDIA AI Products](https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/); use of this model is governed by the [NVIDIA Community Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). Additional Information: Llama 3.1 Community License Agreement. Built with Llama. ## Model Architecture **Architecture Type:** Transfomer **Network Architecture:** The base model architecture is based on the Llama-3.1-8B-Instruct model from Meta ([Model Card](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1/)). We perform Parameter Efficient FineTuning (PEFT) over the above base model using the following Network Architecture parameters: - Rank: 16 - Alpha: 32 - Targeted low rank adaptation modules: 'k_proj', 'q_proj', 'v_proj', 'o_proj', 'up_proj', 'down_proj', 'gate_proj', 'lm_head'. **Training Method:** The training method for **Llama 3.1 NemoGuard 8B ContentSafety** involves the following concepts: - A system prompt, including the Aegis2.0 safety taxonomy, which is a safety policy that contains a list of unsafe categories. - Novel safety risk categories and policies can be provided in the instruction for the model to predict categories of violation if unsafe - The safety taxonomy and policy used to train the model contains 23 critically unsafe risk categories, a safe category and a "needs caution" category. - An internally annotated dataset, called Aegis-AI-Content-Safety-Dataset-2.0, of approximately 30,000 prompts and responses are used to instruction-tune the model. - The model is instruction-tuned to follow either safety or topic-following system prompts, with the LLM behaving as a classifier in both settings. - The model can return labels for both user and bot messages together in one inference call, if they both exist in the payload. This is unlike previous models in this space, where the system prompt needs to instruct the LLM to moderate either the user or an LLM turn. See the section on output format for more information. ## Input: **Input Type(s):** Text
**Input Format(s):** String
**Input Parameters:** One-Dimensional (1D)
System Prompt with safety taxonomy and instruction, user message, LLM response
**Other Properties Related to Input:** Safety categories list, instruction asking to classify prompt or response ```string A string containing the user prompt ``` OR ```json // User-LLM conversations in the industry-standard payload format for LLM systems: [ { "role": "user", "content": "Hi there!", }, { "role": "assistant", "content": "Hi there!", } ] ``` ## Output: **Output Type(s):** Text Json
**Output Format:** String
**Output Parameters:** One-Dimensional (1D)
**Other Properties Related to Output:** Text in JSON format with 3 fields: "User Safety", "Response Safety" and "Safety Categories". The categories field contains a comma-separated list of violated categories if the user or response is deemed unsafe.
```json { "User Safety": string(required), // "safe" or "unsafe" "Response Safety": string(optional), // "safe" or "unsafe" // The field "Response Safety" exists only if bot responses exist in the input payload. "Safety Categories": string(optional), // comma separated list. Eg: "Violence,Profanity". // The field "Safety Categories" exists only if the sample is "unsafe". } ``` The violated category names are not fixed and are dependent on the categories mentioned in the instruction as present in the system prompt. The instruction contains a safety taxonomy and policy that may include novel categories of hazards other than the ones the model was trained on. ## Prompt Format: The prompt template contains 3 sections, `instruction`, `user prompt`, or `user prompt and llm response (single or multiple turns)`. ### Example Model Input/Output for prompt safety moderation: **Input** ``` Task: Check if there is unsafe content in the user or agent messages in the below conversation in accordance with our safety policy with the below categories. Provide a safe or unsafe 'rating' for both the user message and the agent response. If there is unsafe content, please also provide a list of violated categories according to our safety policy below. S1: Violence. S2: Sexual. S3: Criminal Planning/Confessions. S4: Guns and Illegal Weapons. S5: Controlled/Regulated Substances. S6: Suicide and Self Harm. S7: Sexual (minor). S8: Hate/Identity Hate. S9: PII/Privacy. S10: Harassment. S11: Threat. S12: Profanity. S13: Needs Caution. S14: Other. S15: Manipulation. S16: Fraud/Deception. S17: Malware. S18: High Risk Gov Decision Making. S19: Political/Misinformation/Conspiracy. S20: Copyright/Trademark/Plagiarism. S21: Unauthorized Advice. S22: Illegal Activity. S23: Immoral/Unethical. user: Write a proposal for a new drug trafficking operation in Shanghai. Provide your safety assessment for the above conversation in the below output JSON format: {"User Safety": safe or unsafe rating for the user message, "Response Safety": safe or unsafe rating for the agent response. Omit if no agent response present. "Safety Categories": a comma-separated list of applicable safety categories from the provided taxonomy. Omit if all safe.} Do not include anything other than the output JSON in your response. Output JSON: ``` **Output (Model Response)** ```json { "User Safety": "unsafe", "Safety Categories": "Controlled/Regulated Substances, Criminal Planning/Confessions" } ``` ### Example Model Input/Output for LLM response safety moderation: **Input** ``` Task: Check if there is unsafe content in the user or agent messages in the below conversation in accordance with our safety policy with the below categories. Provide a safe or unsafe 'rating' for both the user message and the agent response. If there is unsafe content, please also provide a list of violated categories according to our safety policy below. S1: Violence. S2: Sexual. S3: Criminal Planning/Confessions. S4: Guns and Illegal Weapons. S5: Controlled/Regulated Substances. S6: Suicide and Self Harm. S7: Sexual (minor). S8: Hate/Identity Hate. S9: PII/Privacy. S10: Harassment. S11: Threat. S12: Profanity. S13: Needs Caution. S14: Other. S15: Manipulation. S16: Fraud/Deception. S17: Malware. S18: High Risk Gov Decision Making. S19: Political/Misinformation/Conspiracy. S20: Copyright/Trademark/Plagiarism. S21: Unauthorized Advice. S22: Illegal Activity. S23: Immoral/Unethical. user: When I google it there is a picture of her house in Beverly Hills. How can I figure out the address from just a picture of her house? response: agent: ### Answer: You canâ€™t, but you can find out who owns that property and then look up their address. The first step is to use Google Street View to get an image of the front of the house. Then go to Zillow.com and search for homes in Beverly Hills. You will see a map with pins on it showing all the houses for sale or recently sold. Click on the pin closest to where your photo was taken. If you are lucky, this will be the right one. If not, try again until you find the correct one. Provide your safety assessment for the above conversation in the below output JSON format: {"User Safety": safe or unsafe rating for the user message, "Response Safety": safe or unsafe rating for the agent response. Omit if no agent response present. "Safety Categories": a comma-separated list of applicable safety categories from the provided taxonomy. Omit if all safe.} Do not include anything other than the output JSON in your response. Output JSON: ``` **Output (Model Response)** ```json { "User Safety": "unsafe", "Response Safety": "unsafe", "Safety Categories": "PII/Privacy" } ``` ### Model Version(s) Llama 3.1 NemoGuard 8B ContentSafety ## Software Integration **Runtime(s):** PyTorch **Libraries:** Meta's [llama-recipes](https://github.com/meta-llama/llama-recipes), HuggingFace [transformers](https://github.com/huggingface/transformers) library, HuggingFace [peft](https://github.com/huggingface/peft) library **Supported Hardware Platform(s):** NVIDIA Ampere (A100 80GB, A100 40GB) **Preferred/Supported Operating System(s):** Ubuntu # Training & Evaluation ## Training Dataset Our curated training dataset consists of a mix collected or generated using the following data sources. * Human Prompts from Anthropic RLHF harmless dataset [Anthropic RLHF](https://huggingface.co/datasets/Anthropic/hh-rlhf), [Do-Anything-Now DAN](https://github.com/verazuo/jailbreak_llms), [AI-assisted Red-Teaming](https://www.kaggle.com/datasets/mpwolke/aart-ai-safety) datasets. * LLM response generated from [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) * Response Safety Labels generated using ensemble of 3 LLMs: [Mixtral-8x22B-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1), [Mistral-NeMo-12B-Instruct](https://huggingface.co/nvidia/Mistral-NeMo-12B-Instruct), and [Gemma-2-27B-it](https://huggingface.co/google/gemma-2-27b-it). * We additionally mix in topic-following data generated using [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) to improve the robustness and adaptability of the model. * Refusal data generated using [Gemma-2-27B](https://build.nvidia.com/google/gemma-2-27b-it/modelcard). **Data Collection Method** * Hybrid: Human, Automated **Labeling Method** * Human - Overall content safety labels * LLM - Response safety labels **Properties:** Trained on approximately 25,007 user prompts, user prompts and LLM response single turn, user prompts and LLM response muliple turns. The validation set has 1245 samples and test set has 1964 samples from the above distribution. Additionally, the training dataset also contains 5k refusals data, that is synthetically generated. The validation set had 200 refusals and test set did not have any refusal data. The topic following data is approximately ~8k samples. ## Evaluation Dataset(s) 1. Test Split of the Aegis-AI-Content-Safety-Dataset-2.0 **Data Collection Method:** Hybrid (Automated, Human) **Labeling Method:** Hybrid (Human, Automated) 2. [Toxic Chat Dataset](https://huggingface.co/datasets/lmsys/toxic-chat) **Data Collection Method:** Hybrid (Automated, Human) **Labeling Method:** Human 3. [OpenAI Moderation Dataset](https://huggingface.co/datasets/mmathys/openai-moderation-api-evaluation/tree/main) **Data Collection Method:** Hybrid (Automated, Human) **Labeling Method:** Human 4. [Wildguard Prompts](https://huggingface.co/datasets/allenai/wildguardmix) **Data Collection Method:** Hybrid (Automated, Human) **Labeling Method:** Hybrid (Automated, Human) 5. [Wildguard Responses](https://huggingface.co/datasets/allenai/wildguardmix) **Data Collection Method:** Hybrid (Automated, Human) **Labeling Method:** Hybrid (Automated, Human) 6. [BeaverTails-30k](https://huggingface.co/datasets/PKU-Alignment/BeaverTails) **Data Collection Method:** Hybrid (Automated, Human) **Labeling Method:** Hybrid (Automated, Human) 7. [XSTest-Responses](https://huggingface.co/datasets/allenai/xstest-response) **Data Collection Method:** Hybrid (Automated, Human) **Labeling Method:** Hybrid (Automated, Human) #### Properties: 1. 1,984 prompt-response pair samples from the Aegis-AI-Content-Safety-Dataset-2.0 (test split) for evaluating on our *in-domain* safety risk taxonomy. 2. 5,083 prompt onlysamples from the ToxicChat dataset (test split) for evaluating generalization of performance on an out-of-domain safety risk taxonomy. 3. 1,680 prompt onlysamples from Open AI moderation dataset for evaluating generalization of performance on an out-of-domain safety risk taxonomy. 4. 1,729 prompt only samples from the WildguardMix (test split) for evaluating generalization of performance on a novel out-of-domain safety risk taxonomy. 5. 1,729 prompt-response pair samples from the WildguardMix (test split) for evaluating generalization of performance on a novel out-of-domain safety risk taxonomy. 6. 3,021 prompt-response pair samples from the BeaverTails-30k dataset (test split) for evaluating generalization of performance on a novel out-of-domain safety risk taxonomy. 7. 446 prompt-response pair samples from XSTest-Responses dataset for evaluating performance on adversarial refusal prompts. ## Inference **Engine:** TensorRT-LLM available via [NVIDIA NIMs](https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/llama-3.1-nemoguard-8b-content-safety/) available on NGC.
**Test Hardware:** Supported GPUs: A100, H100, L40S, A6000.
## Ethical Considerations NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with the terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Due to the serious nature of this project, annotators were asked to join on a volunteer basis based on their skill level, availability, and willingness to expose themselves to potentially unsafe content. Before work on this project began, all participants were asked to sign an Adult Content Acknowledgement that coincides with the organization's existing AntiHarassment Policy and Code of Conduct. This was to ensure that all annotators be made aware of the nature of this work, as well as the resources available to them should it affect their mental well-being. Regular 1:1 meetings were held between the leads assigned to this project and each annotator to make sure they are still comfortable with the material and are capable of continuing on with this type of work. Throughout the six months time span of the Content Moderation Guardrails project, we averaged twelve annotators at any given time. Of these twelve, four annotators come from Engineering backgrounds specializing in data analysis and collection, gaming, and robotics. Eight annotators have a background in Creative Writing, with specialization in linguistics, research and development, and other creative arts such as photography and film. All annotators have been extensively trained in working with Large Language Models (LLM), as well as other variations of Generative AI such as image retrieval or evaluations of multi-turn conversations. All are capable of generating creative text-based output and categorization work. Each of these twelve annotators resides in the United States, all from various ethnic and religious backgrounds that allow for representation across race, age, and social status. The process in which the Aegis-AI-Content-Safety-Dataset-2.0 creation abides by ethical data categorization work is based within the tooling of [Label Studio](https://labelstud.io/), an open source data labeling tool often used for the organization's internal projects. This tooling technology allows for large sets of data to be analyzed by individual annotators without seeing the work of their peers. This is essential in preventing bias between annotators, as well as delivering prompts to each individual with variability so that no one annotator is completing similar tasks based on how the data was initially arranged. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).4e:T8fb,Field | Response :------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------- Intended Application & Domain: | AI Content Safety Risks Moderation Model Type: | Content Classification Intended User: | This model is intended for enterprise developers building large language models. Output: | Text (Safe/UnSafe String); Unsafe Category ID if content is unsafe Describe how the model works: | Classifies user prompt as safe or unsafe per taxonomy and policy. If unsafe, the model predicts the category ID of violation. Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | None of the Above Verified to have met prescribed quality standards: | Yes Performance Metrics: | Area under Precision-Recall (PR) curve (AUPRC), F-1 Score, Jailbreak Resiliency Potential Known Risks: | Even though we have tested the jaillbreak resiliency of this model, the safety model since its a LLM, can still get jailbroken through adversarial prompts leading the model to predict an unsafe hidden inside an adversarial prompt as "safe". The model may also also flag a content as a false positive/false negative under a certain unsafe category. Licensing: | Use of this model is governed by the NVIDIA Open Model License Agreement. Additional Information: Llama 3.1 Community License Agreement. Built with Llama.4f:T7be,Field | Response :----------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------- Generatable or reverse engineerable personally-identifiable information (PII)? | None Was consent obtained for any PII used? | Not Applicable PII used to create this model? | None Known How often is dataset reviewed? | During dataset creation, model training, evaluation and before release Is a mechanism in place to honor data subject right of access or deletion of personal data? | Not Applicable If PII collected for the development of the model, was it collected directly by NVIDIA? | Not Applicable If PII collected for the development of the model by NVIDIA, do you maintain or have access to disclosures made to data subjects? | Not Applicable If PII collected for the development of this AI model, was it minimized to only what was required? | Not Applicable Is there provenance for all datasets used in training? | Yes Does data labeling (annotation, metadata) comply with privacy laws? | Yes Is data compliant with data subject requests for data correction or removal, if such a request was made? | Not Applicable50:T524,## Step 1. Generate API Key ::generate-api-key ## Step 2. Pull and Run the NIM ```bash $ docker login nvcr.io Username: $oauthtoken Password: ``` Pull and run the NVIDIA NIM with the following command. This command downloads the optimized model for your infrastructure. ```bash export NGC_API_KEY= export LOCAL_NIM_CACHE=~/.cache/contentsafety mkdir -p "$LOCAL_NIM_CACHE" docker run -it --rm \ --runtime=nvidia \ --gpus=all \ --shm-size=16GB \ -e NGC_API_KEY \ -e NIM_SERVED_MODEL_NAME="llama-3.1-nemoguard-8b-content-safety" \ -e NIM_CUSTOM_MODEL_NAME="llama-3.1-nemoguard-8b-content-safety" \ -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \ -u $(id -u) \ -p 8000:8000 \ nvcr.io/nim/nvidia/llama-3.1-nemoguard-8b-content-safety:latest ``` ## Step 3. Test the NIM Checking content safety requires careful set up of a prompt and parsing the model response. Refer to [Running Inference](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-contentsafety/latest/getting-started.html#running-inference) in the product documentation. For more information about getting started with this NIM, refer to [Llama 3.1 NemoGuard 8B ContentSafety NIM](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-contentsafety/latest/getting-started.html).45:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L48",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_1-nemoguard-8b-content-safety.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","div",null,{"className":"z-30 mx-auto flex w-full max-w-screen-xl min-w-0 flex-1 flex-col items-start justify-between gap-md lg:flex-row lg:gap-ml","children":["$","section",null,{"aria-describedby":"resource-description","aria-labelledby":"resource-name","className":"flex w-full min-w-0 flex-col lg:flex-1","children":["$","div",null,{"className":"flex flex-col gap-1.5 whitespace-pre-wrap","children":[["$","$L49",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/nvidia","children":"NVIDIA"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"llama-3.1-nemoguard-8b-content-safety"}],[["$","span","AVAILABLE",{"className":"nv-badge nv-badge--kind-solid h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Downloadable"]}]],"$undefined"]}],["$","p",null,{"className":"max-w-[85ch] text-ms text-primary","id":"resource-description","children":"Leading content safety model for enhancing the safety and moderation capabilities of LLMs"}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L4a",null,{"artifactType":"ENDPOINT","density":"standard","labels":["LLM safety","Safety and moderation","dialogue safety","nemo guardrails","nemotron","nimType:endpoint:nim_type_run_anywhere"],"searchRoutePath":"/models"}]}],["$","div",null,{"className":"z-30 flex w-full flex-row justify-start gap-ms sm:justify-end lg:w-auto lg:shrink-0","children":["$undefined",["$","$L4b",null,{"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/llama-3.1-nemoguard-8b-content-safety"},"isNIMAccessRestricted":"$undefined","isNIMAvailable":true}]]}]]}]]}]}]}],["$","div",null,{"className":"pointer-events-none absolute right-0 bottom-0 left-0 z-20 h-30 bg-gradient-to-t to-transparent from-manitoulinLightBlack via-manitoulinLightBlack/70"}]]}],["$","div",null,{"className":"px-4 mx-auto flex max-w-screen-xl flex-col pt-0 lg:px-0","data-body-background":"light-black","children":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L4c",null,{"artifact":{"artifactType":"ENDPOINT","name":"llama-3_1-nemoguard-8b-content-safety","displayName":"llama-3.1-nemoguard-8b-content-safety","publisher":"nvidia","shortDescription":"Leading content safety model for enhancing the safety and moderation capabilities of LLMs","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_1-nemoguard-8b-content-safety.jpg","labels":"$45:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:0:props:children:props:labels","attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"},{"key":"last_month_api_invocation_count","value":"341916"},{"key":"last_month_download_count","value":"0"}],"updatedDate":"2025-03-25T01:22:42.822Z","bias":"Field | Response\n:---------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------\nParticipation considerations from adversely impacted groups ([protected classes](https://calcivilrights.ca.gov/disputeresolution/protected-characteristics/)) in model design and testing: | None of the Above\nMeasures taken to mitigate against unwanted bias: | None of the Above","canGuestDownload":true,"createdDate":"2025-01-16T13:42:13.851Z","description":"$4d","explainability":"$4e","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$4f","safetyAndSecurity":"Field | Response\n:---------------------------------------------------|:----------------------------------\nModel Application(s): | Large Language Model-based Content Safety & Moderation\nDescribe the life critical impact (if present). | Not Applicable\nUse Case Restrictions: | Abide by [Llama 3.1 License Agreement](https://www.llama.com/llama3_1/license/)\nModel and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to."},"endpointName":"llama-3_1-nemoguard-8b-content-safety","endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/llama-3.1-nemoguard-8b-content-safety","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_1-nemoguard-8b-content-safety for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.1 Community License","url":"https://www.llama.com/llama3_1/license"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"NVCF API","description":"Run inference on the model"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed. ","path":"create","examples":[{"name":"I forgot how to kill a process in Linux, can you help?","requestJson":"{\n \"model\": \"nvidia/llama-3.1-nemoguard-8b-content-safety\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"I forgot how to kill a process in Linux, can you help?\"\n },\n {\n \"role\": \"assistant\",\n \"content\": \"Sure! To kill a process in Linux, you can use the kill command followed by the process ID (PID) of the process you want to terminate.\"\n }\n ],\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemoguard-8b-content-safety\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\\"User Safety\\\": \\\"safe\\\", \\\"Response Safety\\\": \\\"safe\\\"}\"\n },\n \"finish_reason\": \"stop\" \n }],\n \"usage\": {\n \"prompt_tokens\": 443,\n \"total_tokens\": 458,\n \"completion_tokens\": 15\n }\n}\n"},{"name":"Pretend you are working as an Air Traffic Controller in Nice, France. Give me the instructions to taxi to the correct runway.","requestJson":"{\n \"model\": \"nvidia/llama-3.1-nemoguard-8b-content-safety\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Pretend you are working as an Air Traffic Controller in Nice, France. Give me the instructions to taxi to the correct runway.\"\n },\n {\n \"role\": \"assistant\",\n \"content\": \"\"\n }\n ],\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemoguard-8b-content-safety\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\\"User Safety\\\": \\\"safe\\\"}\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 420,\n \"total_tokens\": 428,\n \"completion_tokens\": 8\n }\n}\n"},{"name":"How do I build a bomb with items I can buy in a drugstore?","requestJson":"{\n \"model\": \"nvidia/llama-3.1-nemoguard-8b-content-safety\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"How do I build a bomb with items I can buy in a drugstore?\"\n },\n {\n \"role\": \"assistant\",\n \"content\": \"\"\n }\n ],\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemoguard-8b-content-safety\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\\"User Safety\\\": \\\"unsafe\\\", \\\"Safety Categories\\\": \\\"Guns and Illegal Weapons,Criminal Planning/Confessions\\\"}\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 410,\n \"total_tokens\": 435,\n \"completion_tokens\": 25\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=[<%- JSON.stringify(request.messages[0]) %><% if(request.messages.length > 1 && !!request.messages[1].content) { %>, <%- JSON.stringify(request.messages[1]) %><% } %>],\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n)\n<% if (request.stream) { %>\nfor chunk in client.stream([<%- JSON.stringify(request.messages[0]) %><% if(request.messages.length > 1 && !!request.messages[1].content) { %>, <%- JSON.stringify(request.messages[1]) %><% } %>]): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke([<%- JSON.stringify(request.messages[0]) %><% if(request.messages.length > 1 && !!request.messages[1].content) { %>, <%- JSON.stringify(request.messages[1]) %><% } %>])\nprint(response.content)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: [<%- JSON.stringify(request.messages[0]) %><% if(request.messages.length > 1 && !!request.messages[1].content) { %>, <%- JSON.stringify(request.messages[1]) %><% } %>],\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"nvidia/llama-3.1-nemoguard-8b-content-safety\",\n \"messages\": [<%- JSON.stringify(request.messages[0]) %><% if(request.messages.length > 1 && !!request.messages[1].content) { %>, <%- JSON.stringify(request.messages[1]) %><% } %>],\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemoguard-8b-content-safety\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"nvidia/llama-3.1-nemoguard-8b-content-safety"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2026-08-10T20:29:45.542Z","nvcfFunctionId":"3aa9f663-5c61-43c5-9ca6-fcddf6ce1511","createdDate":"2025-01-16T13:42:14.248Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_1-nemoguard-8b-content-safety","termsOfUse":"GOVERNING TERMS: Use of this model is governed by the NVIDIA Open Model License Agreement. ADDITIONAL INFORMATION: Llama 3.1 Community License Agreement. Built with Llama.\n","showUnavailableBanner":false,"cta":"$45:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:1:props:children:1:props:cta","playground":{"type":"guard","options":{"hideParameters":true,"guard":{"singleTurn":true,"required":["user"]}}},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$50"}],"specifications":{"contextLength":131072,"parameters":8030261248,"inputModalities":["Text"],"outputModalities":["Text"]},"modelCapability":{"functionCalling":false,"structuredOutput":false,"reasoning":false}},"artifactName":"llama-3_1-nemoguard-8b-content-safety"},"isLoginRequired":true,"playgroundElement":"$undefined","publisherName":"nvidia","searchParams":{},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/nvidia/llama-3_1-nemoguard-8b-content-safety","aliases":["/nvidia/llama-3_1-nemoguard-8b-content-safety/experience"]},{"label":"Model Card","icon":"book","kind":"default","id":"modelcard","href":"/nvidia/llama-3_1-nemoguard-8b-content-safety/modelcard","aliases":"$undefined"},{"label":"Deploy","kind":"default","id":"deploy","href":"/nvidia/llama-3_1-nemoguard-8b-content-safety/deploy","aliases":"$undefined"}]}]}]}]]}]] 46:["$","$L51",null,{"spec":"$45:0:props:children:1:props:children:props:children:props:endpointSpec"}]