The NVIDIA Llama 3.3 70B Instruct FP8 model is the quantized version of the Meta's Llama 3.3 70B Instruct model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Llama 3.3 70B Instruct FP8 model is quantized with TensorRT Model Optimizer.
This model is ready for commercial/non-commercial use.
Third-Party Community Consideration
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA (Meta-Llama-3.3-70B-Instruct) Model Card.
Input Type(s): Text Input Format(s): String Input Parameters: 1D (One Dimensional): Sequences Other Properties Related to Input: Context length up to 128K
Output:
Output Type(s): Text Output Format: String Output Parameters: 1D (One Dimensional): Sequences Other Properties Related to Output: N/A
The model is quantized with nvidia-modelopt v0.27.1
Datasets:
Calibration Dataset: cnn_dailymail
** Data collection method: The dataset is collected by crawling and extracting news articles and their summaries from the CNN and Daily Mail websites.
** Labeling method: The dataset is labeled by having the news articles as input and the corresponding highlight as the gold label summary.
Evaluation Dataset: MMLU, GSM8K_COT, ARC Challenge, IFEVAL
** Data collection method: The data is gathered from various sources.
** Labeling method: The data is labeled by human input and/or algorithmic methods.
Inference:
Engine: Tensor(RT)-LLM Test Hardware: H100
Post Training Quantization
This model was obtained by quantizing the weights and activations of Meta-Llama-3.3-70B-Instruct to FP8 data type, ready for inference with TensorRT-LLM. Only the weights and activations of the linear operators within transformers blocks are quantized. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%.
Usage
Deploy with TensorRT-LLM
To deploy the quantized checkpoint with TensorRT-LLM LLM API, follow the sample codes below:
LLM API sample usage:
from tensorrt_llm import LLM, SamplingParams
def main():
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="nvidia/Llama-3.3-70B-Instruct-FP8")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
# The entry point of the program need to be protected for spawning processes.
if __name__ == '__main__':
main()
Evaluation
The accuracy benchmark results are presented in the table below:
Precision
MMLU
GSM8K_COT
ARC Challenge
IFEVAL
BF16
83.3
95.3
93.7
92.1
FP8
83.2
94.3
93.2
92.2
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 our 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.
Please report security vulnerabilities or NVIDIA AI Concerns here.
