---
language:
- en
license: apache-2.0
library_name: peft
tags:
- trl
- unsloth
- nlp
- code
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
datasets:
- reciperesearch/dolphin-sft-v0.1-preference
pipeline_tag: text-generation
widget:
- messages:
  - role: user
    content: Can you provide ways to eat combinations of bananas and dragonfruits?
---

## Model Summary

The Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties.

### Chat Format

Given the nature of the training data, the Phi-3 Mini-4K-Instruct model is best suited for prompts using the chat format as follows. 
```python
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""
```

### Sample inference code

This code snippets show how to get quickly started with running the model on a GPU: 
```python
pip install peft transformers bitsandbytes accelerate
```
```python
from transformers import AutoModelForCausalLM
from transformers import AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
    "rishiraj/Phi-3-mini-4k-ORPO",
    load_in_4bit = True,
)
tokenizer = AutoTokenizer.from_pretrained("rishiraj/Phi-3-mini-4k-ORPO")

# alpaca_prompt = You MUST copy from above!

inputs = tokenizer(
[
    alpaca_prompt.format(
        "What is a famous tall tower in Paris?", # instruction
        "", # input
        "", # output - leave this blank for generation!
    )
], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
tokenizer.batch_decode(outputs)
```