Fashion_PHI_1-5

Model Description

• Developed by: [Microsoft]
• Model type: [Text Generation]
• Finetuned from model [microsoft/phi-1_5]

How to Use

Phi-1.5 has been integrated in the transformers version 4.30.0. ensure that you are doing the following:

• When loading the model, ensure that trust_remote_code=True is passed as an argument of the from_pretrained() function.

Intended Uses

Given the nature of the training data, Fashion Phi-1.5 is best suited for prompts using the QA format, the chat format. Note that Fashion Phi-1.5 often produces irrelevant text following the main answer. In the following example, we've truncated the answer for illustrative purposes only.

QA

<human>: What can I wear with an olive green bomber jacket for a winter casual outing? Olive Male
<assistant>: Great choice! To wear with an olive green bomber jacket for a winter casual outing consider adding: 1. White or gray graphic T-shirt for a laid-back vibe. 2. Dark denim jeans or cargo pants for a rugged look. 3. High-top sneakers or combat boots for a street-style finish. 4. A plaid flannel shirt or denim jacket for added warmth. 5. A patterned scarf or beanie for a pop of color and style.

How to Get Started with the Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'

Model = 'SSTalha/Fashion_PHI_1-5'
model = AutoModelForCausalLM.from_pretrained(Model, torch_dtype="auto", trust_remote_code=True).to(torch_device)
tokenizer = AutoTokenizer.from_pretrained(Model, trust_remote_code=True)

inputs = tokenizer('''<human>: Have black dress pants and need advice on a shirt for a semi-formal gathering. Any recommendations on colors and styles? Black Male ''', return_tensors="pt", return_attention_mask=False)

inputs = {key: value.to('cuda') for key, value in inputs.items()}

outputs = model.generate(**inputs, max_length=90)

text = tokenizer.batch_decode(outputs)[0]
print(text)