---
library_name: transformers
tags:
- trl
- sft
license: apache-2.0
datasets:
- Mike0307/alpaca-en-zhtw
language:
- zh
pipeline_tag: text-generation
---


## Download the model

The base-model [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) currently relies on 
the latest dev-version transformers and torch.<br>
Also, it needs *trust_remote_code=True* as an argument of the from_pretrained() function.
```
pip install git+https://github.com/huggingface/transformers
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cpu
```

Additionally, LoRA model requires the peft package.
```
pip install peft
```

Now, let's start to download the model. 

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Mike0307/Phi-3-mini-4k-instruct-chinese-lora"
model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    device_map="mps", # FIX mps if not MacOS
    torch_dtype=torch.float32, 
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
```

## Example of inference

```python
input_text = "<|user|>將這五種動物分成兩組。\n老虎、鯊魚、大象、鯨魚、袋鼠 <|end|>\n<|assistant|>"
inputs = tokenizer(input_text, return_tensors="pt").to(torch.device("mps")) # FIX mps if not MacOS

outputs = model.generate(
    **inputs, 
    temperature = 0.0,
    max_length = 500,
    do_sample = False
)

generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)
```