Update README.md
Browse files
README.md
CHANGED
|
@@ -10,12 +10,12 @@ pipeline_tag: text-generation
|
|
| 10 |
tags:
|
| 11 |
- chat
|
| 12 |
---
|
| 13 |
-
# Qwen2.5-3B-Instruct-RK3588-1.1.
|
| 14 |
|
| 15 |
This version of Qwen2.5-3B-Instruct has been converted to run on the RK3588 NPU using ['w8a8', 'w8a8_g128', 'w8a8_g256', 'w8a8_g512'] quantization.
|
| 16 |
This model has been optimized with the following LoRA:
|
| 17 |
|
| 18 |
-
Compatible with RKLLM version: 1.1.
|
| 19 |
|
| 20 |
## Useful links:
|
| 21 |
[Official RKLLM GitHub](https://github.com/airockchip/rknn-llm)
|
|
|
|
| 10 |
tags:
|
| 11 |
- chat
|
| 12 |
---
|
| 13 |
+
# Qwen2.5-3B-Instruct-RK3588-1.1.4
|
| 14 |
|
| 15 |
This version of Qwen2.5-3B-Instruct has been converted to run on the RK3588 NPU using ['w8a8', 'w8a8_g128', 'w8a8_g256', 'w8a8_g512'] quantization.
|
| 16 |
This model has been optimized with the following LoRA:
|
| 17 |
|
| 18 |
+
Compatible with RKLLM version: 1.1.4
|
| 19 |
|
| 20 |
## Useful links:
|
| 21 |
[Official RKLLM GitHub](https://github.com/airockchip/rknn-llm)
|