Instructions to use Fan21/Llama-mt-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Fan21/Llama-mt-lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="Fan21/Llama-mt-lora")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Fan21/Llama-mt-lora") model = AutoModelForCausalLM.from_pretrained("Fan21/Llama-mt-lora") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -68,11 +68,11 @@ def evaluate(
|
|
| 68 |
return output.split("### Response:")[1].strip()
|
| 69 |
instruction = 'write your instruction here'
|
| 70 |
inputs = 'write your inputs here'
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
```
|
|
|
|
| 68 |
return output.split("### Response:")[1].strip()
|
| 69 |
instruction = 'write your instruction here'
|
| 70 |
inputs = 'write your inputs here'
|
| 71 |
+
output= evaluate(instruction,
|
| 72 |
+
input=inputs,
|
| 73 |
+
temperature=0.1,#change the parameters by yourself
|
| 74 |
+
top_p=0.75,
|
| 75 |
+
top_k=40,
|
| 76 |
+
num_beams=4,
|
| 77 |
+
max_new_tokens=128,)
|
| 78 |
```
|