Instructions to use asanchez75/phi3.5-mini-instruct-mcq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use asanchez75/phi3.5-mini-instruct-mcq with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/phi-3.5-mini-instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "asanchez75/phi3.5-mini-instruct-mcq") - Notebooks
- Google Colab
- Kaggle
Upload fine-tuned Phi-3 4-bit LoRA adapters
Browse files
README.md
CHANGED
|
@@ -147,6 +147,8 @@ try:
|
|
| 147 |
except json.JSONDecodeError as e:
|
| 148 |
print(f"\nGenerated output IS NOT valid JSON. Error: {e}")
|
| 149 |
|
|
|
|
|
|
|
| 150 |
## Example Output
|
| 151 |
|
| 152 |
The model aims to generate a valid JSON object structured like the example below. Note that while the training prompt focused on specific keys (question, options, correct_option), the model might also generate related fields like explanation based on patterns learned from the training data.
|
|
|
|
| 147 |
except json.JSONDecodeError as e:
|
| 148 |
print(f"\nGenerated output IS NOT valid JSON. Error: {e}")
|
| 149 |
|
| 150 |
+
```
|
| 151 |
+
|
| 152 |
## Example Output
|
| 153 |
|
| 154 |
The model aims to generate a valid JSON object structured like the example below. Note that while the training prompt focused on specific keys (question, options, correct_option), the model might also generate related fields like explanation based on patterns learned from the training data.
|