Commit
•
d73404e
1
Parent(s):
5ec398b
Update README.md
Browse files
README.md
CHANGED
@@ -48,7 +48,18 @@ Training details:
|
|
48 |
|
49 |
# 2. Usage
|
50 |
|
51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
|
53 |
```python
|
54 |
import torch
|
|
|
48 |
|
49 |
# 2. Usage
|
50 |
|
51 |
+
## 2.1 Usage of Our BF16 Model
|
52 |
+
|
53 |
+
1. Please upgrade the `transformers` package to ensure it supports Gemma-2 models. The current version we are using is `4.42.2`.
|
54 |
+
|
55 |
+
2. Use the following Python script to download our BF16 model
|
56 |
+
|
57 |
+
```python
|
58 |
+
from huggingface_hub import snapshot_download
|
59 |
+
snapshot_download(repo_id="shenzhi-wang/Gemma-2-9B-Chinese-Chat", ignore_patterns=["*.gguf"]) # Download our BF16 model without downloading GGUF models.
|
60 |
+
```
|
61 |
+
|
62 |
+
3. Inference with the BF16 model
|
63 |
|
64 |
```python
|
65 |
import torch
|