Instructions to use morizon/qwen3-4b-structured-output-lora_0702_run_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use morizon/qwen3-4b-structured-output-lora_0702_run_1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "morizon/qwen3-4b-structured-output-lora_0702_run_1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model": "Qwen/Qwen3-4B-Instruct-2507", | |
| "train_jsonl": "data/sft_stage_yaml_v1/train.jsonl", | |
| "val_jsonl": "data/sft_stage_yaml_v1/validation.jsonl", | |
| "out_lora_dir": "/content/lora_structeval_t_run1_yaml_rev3", | |
| "max_seq_len": 2048, | |
| "epochs": 1, | |
| "max_steps": 200, | |
| "lr": 1e-06, | |
| "lora_r": 64, | |
| "lora_alpha": 128, | |
| "bf16": true, | |
| "fp16": false | |
| } | |