Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


phi-2 - bnb 8bits
- Model creator: https://huggingface.co/susnato/
- Original model: https://huggingface.co/susnato/phi-2/




Original model description:
---
license: mit
license_name: microsoft-research-license
license_link: LICENSE
---

**DISCLAIMER**: I don't own the weights to this model, this is a property of Microsoft and taken from their official repository : [microsoft/phi-2](https://huggingface.co/microsoft/phi-2).
The sole purpose of this repository is to use this model through the `transformers` API or to load and use the model using the HuggingFace `transformers` library.


# Usage 

First make sure you have the latest version of the `transformers` installed.

```
pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers
```

Then use the transformers library to load the model from the library itself

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("susnato/phi-2")
tokenizer = AutoTokenizer.from_pretrained("susnato/phi-2")

inputs = tokenizer('''def print_prime(n):
   """
   Print all primes between 1 and n
   """''', return_tensors="pt", return_attention_mask=False)

outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)

```