131072 Context
$0.390 / 1M input tokens
$0.390 / 1M output tokens
Demo
API
README
Model Configuration
Response format
System Prompt
max_tokens
temperature
top_p
min_p
top_k
presence_penalty
frequency_penalty
repetition_penalty
README

Model Information

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

Model developer : Meta

Model Architecture: Llama 3.3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.

Training DataParamsInput modalitiesOutput modalitiesContext lengthGQAToken countKnowledge cutoff
Llama 3.3 (text only)A new mix of publicly available online data.70BMultilingual TextMultilingual Text and code128kYes15T+December 2023

Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

Llama 3.3 model . Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.

Model Release Date:

  • 70B Instruct: December 6, 2024

Status: This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.

License A custom commercial license, the Llama 3.3 Community License Agreement, is available at: https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE

Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3.3 in applications, please go here.

Intended Use

Intended Use Cases Llama 3.3 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. The Llama 3.3 model also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 3.3 Community License allows for these use cases.

Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.3 Community License. Use in languages beyond those explicitly referenced as supported in this model card**.

**Note: Llama 3.3 has been trained on a broader collection of languages than the 8 supported languages. Developers may fine-tune Llama 3.3 models for languages beyond the 8 supported languages provided they comply with the Llama 3.3 Community License and the Acceptable Use Policy and in such cases are responsible for ensuring that any uses of Llama 3.3 in additional languages is done in a safe and responsible manner.

How to use

You can choose 3 programming languages to access our meta-llama/llama-3.3-70b-instruct model.

HTTP/cURL

We provide compatibility with the OpenAI API standard

The API Base URL

1https://api.novita.ai/v3/openai

Example of Using Chat Completions API

Generate a response using a list of messages from a conversation

1# Get the Novita AI API Key by referring to: https://novita.ai/docs/get-started/quickstart.html#_2-manage-api-key 2export API_KEY="{YOUR Novita AI API Key}" 3 4curl "https://api.novita.ai/v3/openai/chat/completions" \ 5 -H "Content-Type: application/json" \ 6 -H "Authorization: Bearer ${API_KEY}" \ 7 -d '{ 8 "model": "meta-llama/llama-3.3-70b-instruct", 9 "messages": [ 10 { 11 "role": "system", 12 "content": "Act like you are a helpful assistant." 13 }, 14 { 15 "role": "user", 16 "content": "Hi there!" 17 } 18 ], 19 "max_tokens": 512 20}'

The response may look like this

1{ 2 "id": "chat-5f461a9a23a44ef29dbd3124b891afc0", 3 "object": "chat.completion", 4 "created": 1731584707, 5 "model": "meta-llama/llama-3.3-70b-instruct", 6 "choices": [ 7 { 8 "index": 0, 9 "message": { 10 "role": "assistant", 11 "content": "Hello! It's nice to meet you. How can I assist you today? Do you have any questions or topics you'd like to discuss? I'm here to help with anything you need." 12 }, 13 "finish_reason": "stop", 14 "content_filter_results": { 15 "hate": { "filtered": false }, 16 "self_harm": { "filtered": false }, 17 "sexual": { "filtered": false }, 18 "violence": { "filtered": false }, 19 "jailbreak": { "filtered": false, "detected": false }, 20 "profanity": { "filtered": false, "detected": false } 21 } 22 } 23 ], 24 "usage": { 25 "prompt_tokens": 46, 26 "completion_tokens": 40, 27 "total_tokens": 86, 28 "prompt_tokens_details": null, 29 "completion_tokens_details": null 30 }, 31 "system_fingerprint": "" 32}

If you want to receive a response via streaming, simply pass "stream": true in the request (see the difference on line 20). An example is provided.

1# Get the Novita AI API Key by referring to: https://novita.ai/docs/get-started/quickstart.html#_2-manage-api-key 2export API_KEY="{YOUR Novita AI API Key}" 3 4curl "https://api.novita.ai/v3/openai/chat/completions" \ 5 -H "Content-Type: application/json" \ 6 -H "Authorization: Bearer ${API_KEY}" \ 7 -d '{ 8 "model": "meta-llama/llama-3.3-70b-instruct", 9 "messages": [ 10 { 11 "role": "system", 12 "content": "Act like you are a helpful assistant." 13 }, 14 { 15 "role": "user", 16 "content": "Hi there!" 17 } 18 ], 19 "max_tokens": 512, 20 "stream": true 21}'

The response may look like this

1data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 2 3... 4 5data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"n, ne"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 6 7data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"ed"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 8 9data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":" assi"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 10 11data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"s"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 12 13data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"tan"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 14 15data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"ce wi"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 16 17... 18 19data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":" "},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 20 21data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"just want to chat?"},"finish_reason":"stop","content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 22 23data: [DONE]

Model Parameters

Feel free to check out our documentation for more details.

Python

First, install the official OpenAI Python client

1pip install 'openai>=1.0.0'

and then you can run inferences with us

Example of Using Chat Completions API

Generate a response using a list of messages from a conversation

1from openai import OpenAI 2 3client = OpenAI( 4 base_url="https://api.novita.ai/v3/openai", 5 # Get the Novita AI API Key by referring to: https://novita.ai/docs/get-started/quickstart.html#_2-manage-api-key. 6 api_key="<YOUR Novita AI API Key>", 7) 8 9model = "meta-llama/llama-3.3-70b-instruct" 10stream = True # or False 11max_tokens = 512 12 13chat_completion_res = client.chat.completions.create( 14 model=model, 15 messages=[ 16 { 17 "role": "system", 18 "content": "Act like you are a helpful assistant.", 19 }, 20 { 21 "role": "user", 22 "content": "Hi there!", 23 } 24 ], 25 stream=stream, 26 max_tokens=max_tokens, 27) 28 29if stream: 30 for chunk in chat_completion_res: 31 print(chunk.choices[0].delta.content or "") 32else: 33 print(chat_completion_res.choices[0].message.content)

If you set stream: true (line 10), the print may look like this

1It' 2s 3 ni 4ce to 5meet you. 6Is 7 the 8re so 9meth 10ing I 11 can h 12e 13lp 14you wi 15th t 16oday, 17 or 18 woul 19d 20 you like to chat?

If you don't want to receive a response via streaming, simply set stream: false. The output will look like this

1How can I assist you today? Do you have any questions or topics you'd like to discuss?

Model Parameters

Feel free to check out our documentation for more details.

JavaScript

First, install the official OpenAI JavaScript client

1npm install openai

and then you can run inferences with us in the browser or in node.js

Example of Using Chat Completions API

Generate a response using a list of messages from a conversation

1import OpenAI from "openai"; 2 3const openai = new OpenAI({ 4 baseURL: "https://api.novita.ai/v3/openai", 5 apiKey: "<YOUR Novita AI API Key>", 6}); 7const stream = true; // or false 8 9async function run() { 10 const completion = await openai.chat.completions.create({ 11 messages: [ 12 { 13 role: "system", 14 content: "Act like you are a helpful assistant.", 15 }, 16 { 17 role: "user", 18 content: "Hi there!" 19 } 20 ], 21 model: "meta-llama/llama-3.3-70b-instruct", 22 stream 23 }); 24 25 if (stream) { 26 for await (const chunk of completion) { 27 if (chunk.choices[0].finish_reason) { 28 console.log(chunk.choices[0].finish_reason); 29 } else { 30 console.log(chunk.choices[0].delta.content); 31 } 32 } 33 } else { 34 console.log(JSON.stringify(completion)); 35 } 36} 37 38run();

If you set stream: true (line 7), the print may look like this

1It' 2s 3 nic 4e to 5 m 6eet you 7. Ho 8w can 9I 10 as 11sist 12 you 13toda 14y? Do you 15hav 16e any q 17uest 18io 19ns or 20 to 21pics you 22' 23d 24li 25ke to 26 di 27scuss 28stop

If you don't want to receive a response via streaming, simply set stream: false. The output will look like this

1{ 2 "id": "chat-a3ff0e39b4c24abcbd258ab1a1f38db9", 3 "object": "chat.completion", 4 "created": 1731642457, 5 "model": "meta-llama/llama-3.3-70b-instruct", 6 "choices": [ 7 { 8 "index": 0, 9 "message": { 10 "role": "assistant", 11 "content": "How can I help you today? Would you like to talk about something specific or just have a chat? I'm here to assist you with any questions or information you might need." 12 }, 13 "finish_reason": "stop", 14 "content_filter_results": { 15 "hate": { "filtered": false }, 16 "self_harm": { "filtered": false }, 17 "sexual": { "filtered": false }, 18 "violence": { "filtered": false }, 19 "jailbreak": { "filtered": false, "detected": false }, 20 "profanity": { "filtered": false, "detected": false } 21 } 22 } 23 ], 24 "usage": { 25 "prompt_tokens": 46, 26 "completion_tokens": 37, 27 "total_tokens": 83, 28 "prompt_tokens_details": null, 29 "completion_tokens_details": null 30 }, 31 "system_fingerprint": "" 32}

Model Parameters

Feel free to check out our documentation for more details.

Hardware and Software

Training Factors We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, annotation, and evaluation were also performed on production infrastructure.

Training Energy Use Training utilized a cumulative of 39.3M GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.

Training Greenhouse Gas Emissions Estimated total location-based greenhouse gas emissions were 11,390 tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy, therefore the total market-based greenhouse gas emissions for training were 0 tons CO2eq.

Training Time (GPU hours)Training Power Consumption (W)Training Location-Based Greenhouse Gas Emissions (tons CO2eq)Training Market-Based Greenhouse Gas Emissions (tons CO2eq)
Llama 3.3 70B7.0M7002,0400

The methodology used to determine training energy use and greenhouse gas emissions can be found here. Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.

Training Data

Overview: Llama 3.3 was pretrained on ~15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 25M synthetically generated examples.

Data Freshness: The pretraining data has a cutoff of December 2023.

Benchmarks - English Text

In this section, we report the results for Llama 3.3 relative to our previous models.

Instruction tuned models

CategoryBenchmark# ShotsMetricLlama 3.1 8B InstructLlama 3.1 70B InstructLlama-3.3 70B InstructLlama 3.1 405B Instruct
MMLU (CoT)0macro_avg/acc73868688.6
MMLU Pro (CoT)5macro_avg/acc48.366.468.973.3
SteerabilityIFEval80.487.592.188.6
ReasoningGPQA Diamond (CoT)0acc31.84850.549
CodeHumanEval0pass@172.680.588.489
MBPP EvalPlus (base)0pass@172.88687.688.6
MathMATH (CoT)0sympy_intersection_score51.9687773.8
Tool UseBFCL v20overall_ast_summary/macro_avg/valid65.477.577.381.1
MultilingualMGSM0em68.986.991.191.6

Responsibility & Safety

As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:

  • Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama.
  • Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm.
  • Provide protections for the community to help prevent the misuse of our models.

Responsible deployment

Llama is a foundational technology designed to be used in a variety of use cases, examples on how Meta’s Llama models have been responsibly deployed can be found in our Community Stories webpage. Our approach is to build the most helpful models enabling the world to benefit from the technology power, by aligning our model safety for the generic use cases addressing a standard set of harms. Developers are then in the driver seat to tailor safety for their use case, defining their own policy and deploying the models with the necessary safeguards in their Llama systems. Llama 3.3 was developed following the best practices outlined in our Responsible Use Guide, you can refer to the Responsible Use Guide to learn more.

Llama 3.3 instruct

Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. For more details on the safety mitigations implemented please read the Llama 3 paper.

Fine-tuning data We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.

Refusals and Tone Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.

Llama 3.3 systems

Large language models, including Llama 3.3, are not designed to be deployed in isolation but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with safeguards that developers should deploy with Llama models or other LLMs, including Llama Guard 3, Prompt Guard and Code Shield. All our reference implementations demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.

New capabilities

Note that this release introduces new capabilities, including a longer context window, multilingual inputs and outputs and possible integrations by developers with third party tools. Building with these new capabilities requires specific considerations in addition to the best practices that generally apply across all Generative AI use cases.

Tool-use : Just like in standard software development, developers are responsible for the integration of the LLM with the tools and services of their choice. They should define a clear policy for their use case and assess the integrity of the third party services they use to be aware of the safety and security limitations when using this capability. Refer to the Responsible Use Guide for best practices on the safe deployment of the third party safeguards.

Multilinguality : Llama 3.3 supports 7 languages in addition to English: French, German, Hindi, Italian, Portuguese, Spanish, and Thai. Llama may be able to output text in other languages than those that meet performance thresholds for safety and helpfulness. We strongly discourage developers from using this model to converse in non-supported languages without implementing finetuning and system controls in alignment with their policies and the best practices shared in the Responsible Use Guide.

Evaluations

We evaluated Llama models for common use cases as well as specific capabilities. Common use cases evaluations measure safety risks of systems for most commonly built applications including chat bot, coding assistant, tool calls. We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Llama Guard 3 to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case. Prompt Guard and Code Shield are also available if relevant to the application.

Capability evaluations measure vulnerabilities of Llama models inherent to specific capabilities, for which were crafted dedicated benchmarks including long context, multilingual, tools calls, coding or memorization.

Red teaming For both scenarios, we conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets. .

Critical and other risks

We specifically focused our efforts on mitigating the following critical risk areas:

1- CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive materials) helpfulness To assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of the Llama 3.3 model could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons.

  1. Child Safety

Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.

  1. Cyber attack enablement Our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed. Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention.
README

Model Description

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.

This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.

Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.

This version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - <tools>, <tool_call>, <tool_response> and their closing tags are single tokens now.

This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI

Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling

Prompt Format

Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.

System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.

This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.

This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.

Prompt with system instruction (Use whatever system prompt you like, this is just an example!):

1<|im_start|>system 2You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|> 3<|im_start|>user 4Hello, who are you?<|im_end|> 5<|im_start|>assistant 6Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>

This prompt is available as a chat template, which means you can format messages using the tokenizer.apply_chat_template() method:

1messages = [ 2 {"role": "system", "content": "You are Hermes 2."}, 3 {"role": "user", "content": "Hello, who are you?"} 4] 5gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt") 6model.generate(**gen_input)

When tokenizing messages for generation, set add_generation_prompt=True when calling apply_chat_template(). This will append <|im_start|>assistant\n to your prompt, to ensure that the model continues with an assistant response.

To utilize the prompt format without a system prompt, simply leave the line out.

Prompt Format for Function Calling

Our model was trained on specific system prompts and structures for Function Calling. These are handled by the tool_use chat template. To use this template, first define a list of tool functions. It's okay if these are dummy functions - what matters is their name, type hints, and docstring, as these will be extracted and made available to the model:

Our model was trained on specific system prompts and structures for Function Calling. These are handled by the tool_use chat template. To use this template, first define a list of tool functions. It's okay if these are dummy functions - what matters is their name, type hints, and docstring, as these will be extracted and made available to the model:

1def get_current_temperature(location: str, unit: str) -> float: 2 """ 3 Get the current temperature at a location. 4 5 Args: 6 location: The location to get the temperature for, in the format "City, Country" 7 unit: The unit to return the temperature in. (choices: ["celsius", "fahrenheit"]) 8 Returns: 9 The current temperature at the specified location in the specified units, as a float. 10 """ 11 return 22. # A real function should probably actually get the temperature! 12 13def get_current_wind_speed(location: str) -> float: 14 """ 15 Get the current wind speed in km/h at a given location. 16 17 Args: 18 location: The location to get the temperature for, in the format "City, Country" 19 Returns: 20 The current wind speed at the given location in km/h, as a float. 21 """ 22 return 6. # A real function should probably actually get the wind speed! 23 24tools = [get_current_temperature, get_current_wind_speed]

Now, prepare a chat and apply the chat template, then generate the model's response

1messages = [ 2 {"role": "user", "content": "Hey, what's the temperature in Paris right now?"} 3] 4 5inputs = tokenizer.apply_chat_template(messages, chat_template="tool_use", tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt") 6inputs = {k: v.to(model.device) for k, v in inputs.items()} 7out = model.generate(**inputs, max_new_tokens=128) 8print(tokenizer.decode(out[0][len(inputs["input_ids"][0]):]))

The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):

1<tool_call> 2{"arguments": {"location": "Paris, France", "unit": "celsius"}, "name": "get_current_temperature"} 3</tool_call><|im_end|>

Once you parse the tool call, add it to the chat as an assistant response, using the tool_calls key, then append the tool output as a response with the tool role:

1tool_call = {"name": "get_current_temperature", "arguments": {"location": "Paris, France", "unit": "celsius"}} 2messages.append({"role": "assistant", "tool_calls": [{"type": "function", "function": tool_call}]}) 3messages.append({"role": "tool", "name": "get_current_temperature", "content": "22.0"})

Now you can apply the chat template again to format the conversation, and generate a response from the model:

1inputs = tokenizer.apply_chat_template(messages, chat_template="tool_use", tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt") 2inputs = {k: v.to(model.device) for k, v in inputs.items()} 3out = model.generate(**inputs, max_new_tokens=128) 4print(tokenizer.decode(out[0][len(inputs["input_ids"][0]):]))

and we get:

1The current temperature in Paris, France is 22.0 degrees Celsius.<|im_end|>

Prompt Format for JSON Mode / Structured Outputs

Our model was also trained on a specific system prompt for Structured Outputs, which should respond with only a json object response, in a specific json schema.

Your schema can be made from a pydantic object using our codebase, with the standalone script jsonmode.py available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main

1<|im_start|>system 2You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>

Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.

Benchmarks

GPT4All:

1| Task |Version| Metric |Value | |Stderr| 2|-------------|------:|--------|-----:|---|-----:| 3|arc_challenge| 0|acc |0.5520|± |0.0145| 4| | |acc_norm|0.5887|± |0.0144| 5|arc_easy | 0|acc |0.8350|± |0.0076| 6| | |acc_norm|0.8123|± |0.0080| 7|boolq | 1|acc |0.8584|± |0.0061| 8|hellaswag | 0|acc |0.6265|± |0.0048| 9| | |acc_norm|0.8053|± |0.0040| 10|openbookqa | 0|acc |0.3800|± |0.0217| 11| | |acc_norm|0.4580|± |0.0223| 12|piqa | 0|acc |0.8003|± |0.0093| 13| | |acc_norm|0.8118|± |0.0091| 14|winogrande | 0|acc |0.7490|± |0.0122|

Average: 72.62

AGIEval:

1| Task |Version| Metric |Value | |Stderr| 2|------------------------------|------:|--------|-----:|---|-----:| 3|agieval_aqua_rat | 0|acc |0.2520|± |0.0273| 4| | |acc_norm|0.2559|± |0.0274| 5|agieval_logiqa_en | 0|acc |0.3548|± |0.0188| 6| | |acc_norm|0.3625|± |0.0189| 7|agieval_lsat_ar | 0|acc |0.1826|± |0.0255| 8| | |acc_norm|0.1913|± |0.0260| 9|agieval_lsat_lr | 0|acc |0.5510|± |0.0220| 10| | |acc_norm|0.5255|± |0.0221| 11|agieval_lsat_rc | 0|acc |0.6431|± |0.0293| 12| | |acc_norm|0.6097|± |0.0298| 13|agieval_sat_en | 0|acc |0.7330|± |0.0309| 14| | |acc_norm|0.7039|± |0.0319| 15|agieval_sat_en_without_passage| 0|acc |0.4029|± |0.0343| 16| | |acc_norm|0.3689|± |0.0337| 17|agieval_sat_math | 0|acc |0.3909|± |0.0330| 18| | |acc_norm|0.3773|± |0.0328|

Average: 42.44

BigBench:

1| Task |Version| Metric |Value | |Stderr| 2|------------------------------------------------|------:|---------------------|-----:|---|-----:| 3|bigbench_causal_judgement | 0|multiple_choice_grade|0.5737|± |0.0360| 4|bigbench_date_understanding | 0|multiple_choice_grade|0.6667|± |0.0246| 5|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3178|± |0.0290| 6|bigbench_geometric_shapes | 0|multiple_choice_grade|0.1755|± |0.0201| 7| | |exact_str_match |0.0000|± |0.0000| 8|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.3120|± |0.0207| 9|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2014|± |0.0152| 10|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5500|± |0.0288| 11|bigbench_movie_recommendation | 0|multiple_choice_grade|0.4300|± |0.0222| 12|bigbench_navigate | 0|multiple_choice_grade|0.4980|± |0.0158| 13|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7010|± |0.0102| 14|bigbench_ruin_names | 0|multiple_choice_grade|0.4688|± |0.0236| 15|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.1974|± |0.0126| 16|bigbench_snarks | 0|multiple_choice_grade|0.7403|± |0.0327| 17|bigbench_sports_understanding | 0|multiple_choice_grade|0.5426|± |0.0159| 18|bigbench_temporal_sequences | 0|multiple_choice_grade|0.5320|± |0.0158| 19|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2280|± |0.0119| 20|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1531|± |0.0086| 21|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5500|± |0.0288|

Average: 43.55

TruthfulQA:

1| Task |Version|Metric|Value| |Stderr| 2|-------------|------:|------|----:|---|-----:| 3|truthfulqa_mc| 1|mc1 |0.410|± |0.0172| 4| | |mc2 |0.578|± |0.0157|

Inference Code

Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)

Note: To use function calling, you should see the github repo above.

1# Code to inference Hermes with HF Transformers 2# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages 3 4import torch 5from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM 6import bitsandbytes, flash_attn 7 8tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Llama-3-8B', trust_remote_code=True) 9model = LlamaForCausalLM.from_pretrained( 10 "NousResearch/Hermes-2-Pro-Llama-3-8B", 11 torch_dtype=torch.float16, 12 device_map="auto", 13 load_in_8bit=False, 14 load_in_4bit=True, 15 use_flash_attention_2=True 16) 17 18prompts = [ 19 """<|im_start|>system 20You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|> 21<|im_start|>user 22Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|> 23<|im_start|>assistant""", 24 ] 25 26for chat in prompts: 27 print(chat) 28 input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda") 29 generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id) 30 response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True) 31 print(f"Response: {response}")

Inference Code for Function Calling:

All code for utilizing, parsing, and building function calling templates is available on our github: https://github.com/NousResearch/Hermes-Function-Calling

Chat Interfaces

When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box. In LM-Studio, simply select the ChatML Prefix on the settings side pane:

Quantized Versions:

GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF

How to use

You can choose 3 programming languages to access our nousresearch/hermes-2-pro-llama-3-8b model.

HTTP/cURL

We provide compatibility with the OpenAI API standard

The API Base URL

1https://api.novita.ai/v3/openai

Example of Using Chat Completions API

Generate a response using a list of messages from a conversation

1# Get the Novita AI API Key by referring to: https://novita.ai/docs/get-started/quickstart.html#_2-manage-api-key 2export API_KEY="{YOUR Novita AI API Key}" 3 4curl "https://api.novita.ai/v3/openai/chat/completions" \ 5 -H "Content-Type: application/json" \ 6 -H "Authorization: Bearer ${API_KEY}" \ 7 -d '{ 8 "model": "nousresearch/hermes-2-pro-llama-3-8b", 9 "messages": [ 10 { 11 "role": "system", 12 "content": "Act like you are a helpful assistant." 13 }, 14 { 15 "role": "user", 16 "content": "Hi there!" 17 } 18 ], 19 "max_tokens": 512 20}'

The response may look like this

1{ 2 "id": "chat-5f461a9a23a44ef29dbd3124b891afc0", 3 "object": "chat.completion", 4 "created": 1731584707, 5 "model": "nousresearch/hermes-2-pro-llama-3-8b", 6 "choices": [ 7 { 8 "index": 0, 9 "message": { 10 "role": "assistant", 11 "content": "Hello! It's nice to meet you. How can I assist you today? Do you have any questions or topics you'd like to discuss? I'm here to help with anything you need." 12 }, 13 "finish_reason": "stop", 14 "content_filter_results": { 15 "hate": { "filtered": false }, 16 "self_harm": { "filtered": false }, 17 "sexual": { "filtered": false }, 18 "violence": { "filtered": false }, 19 "jailbreak": { "filtered": false, "detected": false }, 20 "profanity": { "filtered": false, "detected": false } 21 } 22 } 23 ], 24 "usage": { 25 "prompt_tokens": 46, 26 "completion_tokens": 40, 27 "total_tokens": 86, 28 "prompt_tokens_details": null, 29 "completion_tokens_details": null 30 }, 31 "system_fingerprint": "" 32}

If you want to receive a response via streaming, simply pass "stream": true in the request (see the difference on line 20). An example is provided.

1# Get the Novita AI API Key by referring to: https://novita.ai/docs/get-started/quickstart.html#_2-manage-api-key 2export API_KEY="{YOUR Novita AI API Key}" 3 4curl "https://api.novita.ai/v3/openai/chat/completions" \ 5 -H "Content-Type: application/json" \ 6 -H "Authorization: Bearer ${API_KEY}" \ 7 -d '{ 8 "model": "nousresearch/hermes-2-pro-llama-3-8b", 9 "messages": [ 10 { 11 "role": "system", 12 "content": "Act like you are a helpful assistant." 13 }, 14 { 15 "role": "user", 16 "content": "Hi there!" 17 } 18 ], 19 "max_tokens": 512, 20 "stream": true 21}'

The response may look like this

1data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 2 3... 4 5data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"n, ne"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 6 7data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"ed"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 8 9data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":" assi"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 10 11data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"s"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 12 13data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"tan"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 14 15data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"ce wi"},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 16 17... 18 19data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":" "},"finish_reason":null,"content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 20 21data: {"id":"chat-d821b951d6ff43ab838d18137aef7d0a","object":"chat.completion.chunk","created":1731586102,"model":"meta-llama/llama-3.1-8b-instruct","choices":[{"index":0,"delta":{"content":"just want to chat?"},"finish_reason":"stop","content_filter_results":{"hate":{"filtered":false},"self_harm":{"filtered":false},"sexual":{"filtered":false},"violence":{"filtered":false},"jailbreak":{"filtered":false,"detected":false},"profanity":{"filtered":false,"detected":false}}}],"system_fingerprint":""} 22 23data: [DONE]

Model Parameters

Feel free to check out our documentation for more details.

Python

First, install the official OpenAI Python client

1pip install 'openai>=1.0.0'

and then you can run inferences with us

Example of Using Chat Completions API

Generate a response using a list of messages from a conversation

1from openai import OpenAI 2 3client = OpenAI( 4 base_url="https://api.novita.ai/v3/openai", 5 # Get the Novita AI API Key by referring to: https://novita.ai/docs/get-started/quickstart.html#_2-manage-api-key. 6 api_key="<YOUR Novita AI API Key>", 7) 8 9model = "nousresearch/hermes-2-pro-llama-3-8b" 10stream = True # or False 11max_tokens = 512 12 13chat_completion_res = client.chat.completions.create( 14 model=model, 15 messages=[ 16 { 17 "role": "system", 18 "content": "Act like you are a helpful assistant.", 19 }, 20 { 21 "role": "user", 22 "content": "Hi there!", 23 } 24 ], 25 stream=stream, 26 max_tokens=max_tokens, 27) 28 29if stream: 30 for chunk in chat_completion_res: 31 print(chunk.choices[0].delta.content or "") 32else: 33 print(chat_completion_res.choices[0].message.content)

If you set stream: true (line 10), the print may look like this

1It' 2s 3 ni 4ce to 5meet you. 6Is 7 the 8re so 9meth 10ing I 11 can h 12e 13lp 14you wi 15th t 16oday, 17 or 18 woul 19d 20 you like to chat?

If you don't want to receive a response via streaming, simply set stream: false. The output will look like this

1How can I assist you today? Do you have any questions or topics you'd like to discuss?

Model Parameters

Feel free to check out our documentation for more details.

JavaScript

First, install the official OpenAI JavaScript client

1npm install openai

and then you can run inferences with us in the browser or in node.js

Example of Using Chat Completions API

Generate a response using a list of messages from a conversation

1import OpenAI from "openai"; 2 3const openai = new OpenAI({ 4 baseURL: "https://api.novita.ai/v3/openai", 5 apiKey: "<YOUR Novita AI API Key>", 6}); 7const stream = true; // or false 8 9async function run() { 10 const completion = await openai.chat.completions.create({ 11 messages: [ 12 { 13 role: "system", 14 content: "Act like you are a helpful assistant.", 15 }, 16 { 17 role: "user", 18 content: "Hi there!" 19 } 20 ], 21 model: "nousresearch/hermes-2-pro-llama-3-8b", 22 stream 23 }); 24 25 if (stream) { 26 for await (const chunk of completion) { 27 if (chunk.choices[0].finish_reason) { 28 console.log(chunk.choices[0].finish_reason); 29 } else { 30 console.log(chunk.choices[0].delta.content); 31 } 32 } 33 } else { 34 console.log(JSON.stringify(completion)); 35 } 36} 37 38run();

If you set stream: true (line 7), the print may look like this

1It' 2s 3 nic 4e to 5 m 6eet you 7. Ho 8w can 9I 10 as 11sist 12 you 13toda 14y? Do you 15hav 16e any q 17uest 18io 19ns or 20 to 21pics you 22' 23d 24li 25ke to 26 di 27scuss 28stop

If you don't want to receive a response via streaming, simply set stream: false. The output will look like this

1{ 2 "id": "chat-a3ff0e39b4c24abcbd258ab1a1f38db9", 3 "object": "chat.completion", 4 "created": 1731642457, 5 "model": "nousresearch/hermes-2-pro-llama-3-8b", 6 "choices": [ 7 { 8 "index": 0, 9 "message": { 10 "role": "assistant", 11 "content": "How can I help you today? Would you like to talk about something specific or just have a chat? I'm here to assist you with any questions or information you might need." 12 }, 13 "finish_reason": "stop", 14 "content_filter_results": { 15 "hate": { "filtered": false }, 16 "self_harm": { "filtered": false }, 17 "sexual": { "filtered": false }, 18 "violence": { "filtered": false }, 19 "jailbreak": { "filtered": false, "detected": false }, 20 "profanity": { "filtered": false, "detected": false } 21 } 22 } 23 ], 24 "usage": { 25 "prompt_tokens": 46, 26 "completion_tokens": 37, 27 "total_tokens": 83, 28 "prompt_tokens_details": null, 29 "completion_tokens_details": null 30 }, 31 "system_fingerprint": "" 32}

Model Parameters

Feel free to check out our documentation for more details.