Instructions to use vicgalle/phi-2-contextual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use vicgalle/phi-2-contextual with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("cognitivecomputations/dolphin-2_6-phi-2") model = PeftModel.from_pretrained(base_model, "vicgalle/phi-2-contextual") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ A lightweight model (2.8B) with enhanced RAG capabilities, with lower risk of ha
|
|
| 15 |
|
| 16 |
This is a DPO fine-tune of the Phi-2 architecture (in particular, dolphin-2_6-phi-2) over the dataset https://huggingface.co/datasets/jondurbin/contextual-dpo-v0.1.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
## Usage
|
| 19 |
|
| 20 |
Load the model as
|
|
|
|
| 15 |
|
| 16 |
This is a DPO fine-tune of the Phi-2 architecture (in particular, dolphin-2_6-phi-2) over the dataset https://huggingface.co/datasets/jondurbin/contextual-dpo-v0.1.
|
| 17 |
|
| 18 |
+

|
| 19 |
+
|
| 20 |
## Usage
|
| 21 |
|
| 22 |
Load the model as
|