itman-inteli/nsync-sprint4-qwen-fine-tuned

Qwen Curadobia Moda

Modelo Qwen 2.5 0.5B fine-tuned para consultoria de moda em português.

Uso

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("seu-username/qwen-curadobia-moda")
model = AutoModelForCausalLM.from_pretrained("seu-username/qwen-curadobia-moda")

prompt = "<|user|>\nComo usar gola alta?\n<|assistant|>\n"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.3)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)