Qwen2.5-7B Support Tone

Official adapter · maintained by ModelForgeLab

LoRA that nudges responses toward a concise, empathetic support-desk register without changing task capabilities.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base, "modelforgelab/qwen25-7b-support-tone")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• peft>=0.10
• transformers>=4.44