Commit
•
79b5f16
1
Parent(s):
d5825dd
Update README.md
Browse files
README.md
CHANGED
|
@@ -92,4 +92,9 @@ outputs = model.generate(
|
|
| 92 |
)
|
| 93 |
response = outputs[0][input_ids.shape[-1] :]
|
| 94 |
print(tokenizer.decode(response, skip_special_tokens=True))
|
| 95 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
)
|
| 93 |
response = outputs[0][input_ids.shape[-1] :]
|
| 94 |
print(tokenizer.decode(response, skip_special_tokens=True))
|
| 95 |
+
```
|
| 96 |
+
|
| 97 |
+
## 2.2 Usage of Our GGUF Models
|
| 98 |
+
|
| 99 |
+
1. Download our GGUF models from the [gguf_models folder](https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat/tree/main/gguf_models).
|
| 100 |
+
2. Use the GGUF models with [LM Studio](https://lmstudio.ai/) version 0.2.26.
|