| --- |
| base_model: distilgpt2 |
| tags: |
| - career-advice |
| - ai-industry |
| - "2025" |
| - lora |
| - distilgpt2 |
| license: mit |
| --- |
| |
| # AI Job Navigator Model |
|
|
| This is a fine-tuned `distilgpt2` model using LoRA, trained on a small dataset to provide career advice for the AI industry in 2025. |
|
|
| ## Model Details |
| - **Base Model**: distilgpt2 |
| - **Fine-tuning Method**: LoRA |
| - **Training Data**: 16 samples (148,668 characters) of AI industry career advice |
| - **Training Steps**: 10 steps, 5 epochs |
| - **Loss**: ~9.67 to 11.61 |
|
|
| ## Usage |
| You can load and use the model as follows: |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| from peft import PeftModel |
| |
| base_model = AutoModelForCausalLM.from_pretrained("distilgpt2") |
| tokenizer = AutoTokenizer.from_pretrained("jinv2/ai-job-navigator-model") |
| model = PeftModel.from_pretrained(base_model, "jinv2/ai-job-navigator-model") |
| |
| prompt = "根据最新的AI行业趋势，提供2025年的职业建议：" |
| inputs = tokenizer(prompt, return_tensors="pt") |
| outputs = model.generate(**inputs, max_length=200, do_sample=True, temperature=0.7, top_k=50, top_p=0.9) |
| print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
| |
