Update README.md
Browse files
README.md
CHANGED
|
@@ -40,4 +40,13 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 40 |
|
| 41 |
### Framework versions
|
| 42 |
|
| 43 |
-
- PEFT 0.6.3.dev0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
### Framework versions
|
| 42 |
|
| 43 |
+
- PEFT 0.6.3.dev0
|
| 44 |
+
|
| 45 |
+
```[python]
|
| 46 |
+
from peft import PeftModel, PeftConfig
|
| 47 |
+
from transformers import AutoModelForCausalLM
|
| 48 |
+
|
| 49 |
+
config = PeftConfig.from_pretrained("hajili/zephyr-7b-beta-dolly-azerbaijani")
|
| 50 |
+
model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
|
| 51 |
+
model = PeftModel.from_pretrained(model, "hajili/zephyr-7b-beta-dolly-azerbaijani")
|
| 52 |
+
```
|