metadata
license: mit
language:
- en
- fr
base_model:
- microsoft/Phi-3-mini-4k-instruct
pipeline_tag: text-generation
tags:
- nlp
- code
- onnx
- amd
microsoft/Phi-3-mini-4k-instruct
Introduction
This model was created by applying Quark with calibration samples from Pile dataset, and applying onnxruntime-genai model builder to convert to ONNX.Quantization Strategy
- AWQ / Group 128 / Asymmetric / FP32 activations
Quick Start
For quickstart, refer to AMD RyzenAI-SW-EA
Evaluation scores
The perplexity measurement is run on the wikitext-2-raw-v1 (raw data) dataset provided by Hugging Face. Perplexity score measured for prompt length 2k is 6.988726.
License
Modifications copyright(c) 2024 Advanced Micro Devices,Inc. All rights reserved.
license: MIT license