Loss is applied only to the final assistant output,
while intermediate reasoning (Chain-of-Thought) is masked.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2from peft import PeftModel
3import torch
4
5base = "Qwen/Qwen3-4B-Instruct-2507"
6adapter = "your_id/your-repo"
7
8tokenizer = AutoTokenizer.from_pretrained(base)
9model = AutoModelForCausalLM.from_pretrained(
10 base,
11 torch_dtype=torch.float16,
12 device_map="auto",
13)
14model = PeftModel.from_pretrained(model, adapter)
Training data: Local file: /content/drive/MyDrive/Colab Notebooks/LLMAdvanced_MainCompetition/merged_dataset_final_clean.jsonl
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
