amd
/

Llama-3.2-3B-Instruct-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Model card Files Files and versions Community

uday610 commited on 9 days ago

Commit

7faedd6

•

1 Parent(s): 4781d25

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -7,9 +7,9 @@ base_model:
 # meta-llama/Llama-3.2-3B-Instruct
 - ## Introduction
-  This model was created by applying [Quark](https://quark.docs.amd.com/latest/index.html) with calibration samples from Pile dataset, and applying [onnxruntime-genai model builder](https://github.com/microsoft/onnxruntime-genai/tree/main/src/python/py/models) to convert to ONNX.
 - ## Quantization Strategy
-  - AWQ / Group 128 / Asymmetric / FP32 activations
 - ## Quick Start
   For quickstart, refer to npu-llm-artifacts_1.3.zip available in [RyzenAI-SW-EA](https://account.amd.com/en/member/ryzenai-sw-ea.html)

 # meta-llama/Llama-3.2-3B-Instruct
 - ## Introduction
+  This model was created using Quark Quantization, followed by OGA Model Builder, and finalized with post-processing for NPU deployment.
 - ## Quantization Strategy
+  - AWQ / Group 128 / Asymmetric / BF16 activations
 - ## Quick Start
   For quickstart, refer to npu-llm-artifacts_1.3.zip available in [RyzenAI-SW-EA](https://account.amd.com/en/member/ryzenai-sw-ea.html)