Synthetic data comparison
Collection
Masters Thesis on comparing models finetuned using different strategies for generating synthetic data. • 6 items • Updated
Model Card for out_1
This model is a fine-tuned version of Qwen/Qwen2.5-Coder-3B-Instruct. It has been trained using TRL.
Quick start
from transformers import pipeline
question = "Write a Python function to implement insertion sort on a list of floating-point numbers and return the sorted list."
generator = pipeline("text-generation", model="Luca0867/complexity_evolved_selfinstruct")
output = generator([{"role": "user", "content": question}], max_new_tokens=1024, return_full_text=False)[0]
print(output["generated_text"])
Training procedure
This model was trained with SFT.
Framework versions
- TRL: 1.1.0
- Transformers: 5.5.4
- Pytorch: 2.10.0+cu128
- Datasets: 4.8.4
- Tokenizers: 0.22.2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support