Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,14 @@ tags:
|
|
| 7 |
|
| 8 |
# InterLM2-Chat NF4 Quant
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
## Quantization config
|
| 11 |
|
| 12 |
```python
|
|
|
|
| 7 |
|
| 8 |
# InterLM2-Chat NF4 Quant
|
| 9 |
|
| 10 |
+
## Usage
|
| 11 |
+
|
| 12 |
+
As of 2024/1/17, Transformers must be installed from source and bitsandbytes >=0.42.0 is required in order to load serialized 4-bit quants.
|
| 13 |
+
|
| 14 |
+
```bash
|
| 15 |
+
pip install -U git+https://github.com/huggingface/transformers bitsandbytes
|
| 16 |
+
```
|
| 17 |
+
|
| 18 |
## Quantization config
|
| 19 |
|
| 20 |
```python
|