| base_model: meta-llama/Llama-3.3-70B-Instruct | |
| library_name: peft | |
| # LoRA Adapter for SFT | |
| This is a LoRA (Low-Rank Adaptation) adapter trained using supervised fine-tuning (SFT). | |
| ## Base Model | |
| - **Base Model**: `meta-llama/Llama-3.3-70B-Instruct` | |
| - **Adapter Type**: LoRA | |
| - **Task**: Supervised Fine-Tuning | |
| ## Usage | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| from peft import PeftModel | |
| # Load base model and tokenizer | |
| base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.3-70B-Instruct") | |
| tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.3-70B-Instruct") | |
| # Load LoRA adapter | |
| model = PeftModel.from_pretrained(base_model, "thejaminator/year_2026_misaligned_hf_sft-20251022") | |
| ``` | |
| ## Training Details | |
| This adapter was trained using supervised fine-tuning on conversation data to improve the model's ability to follow instructions and generate helpful responses. | |