---
base_model: unsloth/phi-3.5-mini-instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
pipeline_tag: text-generation
---
## Model Summary

EpistemeAI/Iceball-Phi-3.5-mini-instruct-shareGPT-v1.0 is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.

<script type='text/javascript' src='https://storage.ko-fi.com/cdn/widget/Widget_2.js'></script><script type='text/javascript'>kofiwidget2.init('Support Me on Ko-fi', '#29abe0', 'C0C8127LWN');kofiwidget2.draw();</script> 


🏡 [Phi-3 Portal](https://azure.microsoft.com/en-us/products/phi-3) <br>
📰 [Phi-3 Microsoft Blog](https://aka.ms/phi3.5-techblog) <br>
📖 [Phi-3 Technical Report](https://arxiv.org/abs/2404.14219) <br>
👩‍🍳 [Phi-3 Cookbook](https://github.com/microsoft/Phi-3CookBook) <br>
🖥️ [Try It](https://aka.ms/try-phi3.5mini) <br>

**EpistemeAI/Iceball-Phi-3.5-mini-instruct-shareGPT-v1.0  - Phi-3.5**: [[mini-instruct]](https://huggingface.co/microsoft/Phi-3.5-mini-instruct); [[MoE-instruct]](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct) ; [[vision-instruct]](https://huggingface.co/microsoft/Phi-3.5-vision-instruct)

## Intended Uses

### Primary Use Cases

The model is intended for commercial and research use in multiple languages. The model provides uses for general purpose AI systems and applications which require:

1) Memory/compute constrained environments
2) Latency bound scenarios
3) Strong reasoning (especially code, math and logic)

Our model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features. 

## Usage

### Requirements
Phi-3 family has been integrated in the `4.43.0` version of `transformers`. The current `transformers` version can be verified with: `pip list | grep transformers`.

Examples of required packages:
```
flash_attn==2.5.8
torch==2.3.1
accelerate==0.31.0
transformers==4.43.0
```

Phi-3.5-mini-instruct is also available in [Azure AI Studio](https://aka.ms/try-phi3.5mini)

### Tokenizer

Phi-3.5-mini-Instruct supports a vocabulary size of up to `32064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3.5-mini-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size.

### Input Formats
Given the nature of the training data, the Phi-3.5-mini-instruct model is best suited for prompts using the chat format as follows:

```
<|system|>
You are a helpful assistant.<|end|>
<|user|>
How to explain Internet for a medieval knight?<|end|>
<|assistant|>
```

### Loading the model locally
After obtaining the Phi-3.5-mini-instruct model checkpoint, users can use this sample code for inference.

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
torch.random.manual_seed(0)
model = AutoModelForCausalLM.from_pretrained(
    "EpistemeAI/Iceball-Phi-3.5-mini-instruct-shareGPT-v1.0", 
    device_map="cuda", 
    torch_dtype="auto", 
    trust_remote_code=True, 
)
tokenizer = AutoTokenizer.from_pretrained("EpistemeAI/Iceball-Phi-3.5-mini-instruct-shareGPT-v1.0")
messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)
generation_args = {
    "max_new_tokens": 500,
    "return_full_text": False,
    "temperature": 0.0,
    "do_sample": False,
}
output = pipe(messages, **generation_args)
print(output[0]['generated_text'])
```

Notes: If you want to use flash attention, call _AutoModelForCausalLM.from_pretrained()_ with _attn_implementation="flash_attention_2"_


# Uploaded  model

- **Developed by:** EpistemeAI
- **License:** apache-2.0
- **Finetuned from model :** unsloth/phi-3.5-mini-instruct-bnb-4bit

This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)