Ntkt Conversation Vietnamese Full Text Qwen3.5 0.8b Sft

--- base_model: Qwen/Qwen3.5-0.8B library_name: peft pipeline_tag: text-generation license: apache-2.0 datasets: - bihungba1101/slam-en-es-vietnamese-prompts tags: - base_model:adapter:Qwen/Qwen3.5-0.8B - lora - sft - knowledge-tracing - vietnamese - unsloth --- # Qwen3.5 0.8B NTKT Vietnamese Conversation SFT This PEFT LoRA adapter fine-tunes [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) for conversational knowledge tracing. It predicts `Correct` or `Incorrect` from a learner's Vietnamese interaction history represented as full text. ## Training - Method: supervised fine-tuning with assistant-only loss - Context length: 15,000 tokens - Steps: 100 - Effective batch size: 8 - LoRA rank/alpha: 16/16 - Trainable parameters: 6,389,760 (0.74%) - Final training loss: 0.3562 [View the training run on Weights & Biases](https://wandb.ai/ielts-science/NTKT-SLAM/runs/uakr84g0). ## Evaluation Evaluation used a learner-disjoint validation split with 115,853 labeled predictions across 2,361 conversations. | Metric | Value | | --- | ---: | | Accuracy | 0.7326 | | F1 | 0.8287 | | Precision | 0.7580 | | Recall | 0.9139 | | ROC-AUC | 0.7320 | | Brier score | 0.1784 | | Log loss | 0.5323 | ## Usage ```python from peft import AutoPeftModelForCausalLM from transformers import AutoTokenizer repo_id = "bihungba1101/ntkt-conversation-vietnamese-full-text-qwen3.5-0.8b-sft" model = AutoPeftModelForCausalLM.from_pretrained(repo_id, device_map="auto") tokenizer = AutoTokenizer.from_pretrained(repo_id) ``` The adapter expects the included chat template and the same full-text conversation representation used during training. ## Framework versions - PEFT 0.18.1 - TRL 0.23.1 - Transformers 5.2.0 - PyTorch 2.10.0+cu128 - Datasets 4.3.0 - Tokenizers 0.22.2

Source context: 423 downloads · 0 likes · Pipeline text-generation · Library peft · Repo bihungba1101/ntkt-conversation-vietnamese-full-text-qwen3.5-0.8b-sft