Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ tags:
|
|
| 3 |
- npu
|
| 4 |
- amd
|
| 5 |
- llama3.1
|
| 6 |
-
-
|
| 7 |
---
|
| 8 |
|
| 9 |
This model is [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) AWQ quantized and converted version to run on the [NPU installed Ryzen AI PC](https://github.com/amd/RyzenAI-SW/issues/18), for example, Ryzen 9 7940HS Processor.
|
|
@@ -16,6 +16,11 @@ This model has only been tested on RyzenAI for Windows 11. It does not work in L
|
|
| 16 |
|
| 17 |
RoPE support is not yet complete, but it has been confirmed that the perplexity is lower than Llama 3.
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
### setup
|
| 21 |
In cmd windows.
|
|
|
|
| 3 |
- npu
|
| 4 |
- amd
|
| 5 |
- llama3.1
|
| 6 |
+
- RyzenAI
|
| 7 |
---
|
| 8 |
|
| 9 |
This model is [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) AWQ quantized and converted version to run on the [NPU installed Ryzen AI PC](https://github.com/amd/RyzenAI-SW/issues/18), for example, Ryzen 9 7940HS Processor.
|
|
|
|
| 16 |
|
| 17 |
RoPE support is not yet complete, but it has been confirmed that the perplexity is lower than Llama 3.
|
| 18 |
|
| 19 |
+
2024/07/30
|
| 20 |
+
- [Ryzen AI Software 1.2](https://ryzenai.docs.amd.com/en/latest/) has been released. Please note that this model is based on [Ryzen AI Software 1.1](https://ryzenai.docs.amd.com/en/1.1/index.html) and operation with 1.2 has not been confirmed.
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
|
| 25 |
### setup
|
| 26 |
In cmd windows.
|