Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: gpl-3.0
|
| 3 |
---
|
| 4 |
### 4-bit quantization and 128 groupsize for LLaMA 7B
|
|
|
|
|
|
|
| 5 |
Consumes approximately 5.4G of graphics memory
|
| 6 |
```text
|
| 7 |
"input":the mean of life is
|
|
|
|
| 2 |
license: gpl-3.0
|
| 3 |
---
|
| 4 |
### 4-bit quantization and 128 groupsize for LLaMA 7B
|
| 5 |
+
|
| 6 |
+
This is a Chinese instruction-tuning lora checkpoint based on llama-13B from [this repo's](https://github.com/Facico/Chinese-Vicuna) work
|
| 7 |
Consumes approximately 5.4G of graphics memory
|
| 8 |
```text
|
| 9 |
"input":the mean of life is
|