pooja-ganesh
commited on
Commit
•
ac621b8
1
Parent(s):
7a66971
Update README.md
Browse files
README.md
CHANGED
@@ -17,9 +17,9 @@ tags:
|
|
17 |
- ## Introduction
|
18 |
This model was created using Quark Quantization, followed by OGA Model Builder, and finalized with post-processing for NPU deployment.
|
19 |
- ## Quantization Strategy
|
20 |
-
- AWQ / Group 128 / Asymmetric / BF16 activations
|
21 |
- ## Quick Start
|
22 |
-
For quickstart, refer to
|
23 |
|
24 |
#### Evaluation scores
|
25 |
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.
|
|
|
17 |
- ## Introduction
|
18 |
This model was created using Quark Quantization, followed by OGA Model Builder, and finalized with post-processing for NPU deployment.
|
19 |
- ## Quantization Strategy
|
20 |
+
- AWQ / Group 128 / Asymmetric / BF16 activations / UINT4 Weights
|
21 |
- ## Quick Start
|
22 |
+
For quickstart, refer to npu-llm-artifacts_1.3.0.zip available in [RyzenAI-SW-EA](https://account.amd.com/en/member/ryzenai-sw-ea.html)
|
23 |
|
24 |
#### Evaluation scores
|
25 |
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.
|