Downloads · 30 days
58
59% of all-time downloads
damBruh/skyyrose-brand-voice-llm
skyyrose-brand-voice-llm is a machine learning model from damBruh. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Fine-tuned brand voice model for SkyyRose luxury streetwear. Uses LoRA adapters on Qwen/Qwen2.5-0.5B-Instruct.
Downloads · 30 days
58
59% of all-time downloads
All-time downloads
98
Public
Repo size
124 MB
Likes
0
Public
Click a slice to open those files.
.json42.6 MB · 39%
From the Hugging Face model README
Fine-tuned brand voice model for SkyyRose luxury streetwear. Uses LoRA adapters on Qwen/Qwen2.5-0.5B-Instruct.
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
# Load base model and LoRA adapter
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "damBruh/skyyrose-brand-voice-llm")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
# Generate SkyyRose brand voice content
prompt = """<|im_start|>system
You are SkyyRose's brand voice - a luxury streetwear brand from Oakland, California.
<|im_end|>
<|im_start|>user
Write a product description for a rose gold hoodie.
<|im_end|>
<|im_start|>assistant
"""
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=300, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Prompt: "Write a product description for rose gold joggers."
Output: "Introducing the SkyyRose Signature Joggers - where Oakland street culture meets luxury comfort. Crafted in our iconic rose gold hue, these premium joggers embody effortless sophistication..."
Prompt: "Write an Instagram caption for a new collection drop."
Output: "New pieces. Same soul. The latest from SkyyRose - where Oakland authenticity meets global luxury. Limited quantities. Timeless style. 🌹 #WhereloveMeetsLuxury"
Apache 2.0