| license: apache-2.0 | |
| tags: | |
| - tool-calling | |
| - fine-tuned | |
| - spectra | |
| # test_p400_t1_e3 | |
| This model was fine-tuned using **Spectra** by [Axionic Labs](https://axionic.ai). | |
| ## Model Details | |
| - **Base Model**: Qwen/Qwen2.5-0.5B-Instruct | |
| - **Training Method**: SFT | |
| - **Fine-tuned by**: Spectra Pipeline | |
| ## Usage | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model = AutoModelForCausalLM.from_pretrained("aditya123579/test_p400_t1_e3") | |
| tokenizer = AutoTokenizer.from_pretrained("aditya123579/test_p400_t1_e3") | |
| # Your inference code here | |
| ``` | |
| ## About Spectra | |
| Spectra is an automated RL pipeline for creating lightweight, task-specific tool-calling agents. | |
| Learn more at [axionic.ai](https://axionic.ai). | |