Update README.md
#4
by thawani - opened
README.md
CHANGED
|
@@ -9,4 +9,20 @@ complete model with delta patch applied
|
|
| 9 |
|
| 10 |
- No unnecessary changes
|
| 11 |
- Same format
|
| 12 |
-
- No quantization
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
- No unnecessary changes
|
| 11 |
- Same format
|
| 12 |
+
- No quantization
|
| 13 |
+
|
| 14 |
+
# Setup
|
| 15 |
+
```bash
|
| 16 |
+
# Install FastChat
|
| 17 |
+
pip3 install fschat
|
| 18 |
+
|
| 19 |
+
# Install the latest main branch of huggingface/transformers
|
| 20 |
+
pip3 install git+https://github.com/huggingface/transformers
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
+
# Usage
|
| 24 |
+
```bash
|
| 25 |
+
python3 -m fastchat.serve.cli --model-name eachadea/vicuna-13b
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
See more at https://github.com/lm-sys/FastChat
|