README.md

metadata

language:
  - en
tags:
  - text-generation
  - Qwen
  - prompt-engineering
  - instruction-tuning
license: apache-2.0
base_model: Qwen/Qwen3-0.6B

Qwen3-0.6B Awesome Prompts Fine-tune

Fine-tuned version of Qwen/Qwen3-0.6B on the awesome-chatgpt-prompts dataset for prompt generation tasks.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Ontario/qwen3-0.6b-awesome-prompts")
tokenizer = AutoTokenizer.from_pretrained("Ontario/qwen3-0.6b-awesome-prompts")

def generate_prompt(role):
    messages = [{"role": "user", "content": f"Generate a prompt for: {role}"}]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    inputs = tokenizer(text, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

print(generate_prompt("Data Scientist"))