xinyuema/llm-course-hw3-lora

Model Card for Model ID

Model Details

A base model OuteAI/Lite-Oute-1-300M-Instruct was fine-tuned on a tweet sentiment dataset cardiffnlp/tweet_eval in order to determine tweets tonality by positive, neutral or negative.

Model Description

SYSTEM PROMPT:

You are a tweet sentiment classifier. For each tweet input, analyze its sentiment and output exactly one word: "negative", "neutral", or "positive". Do not include any extra text.

But the model is not trained to return only the sentiment name.
So we designed a custom LoRA Linear layer to achive PEFT of this model, by replacing the k_proj and v_proj layers to modify the initial model.

Training Details

batch_size=16 rank = 8 alpha = 16 lr = 5e-6

The model achieved 0.40 macro f1-score （initial 0.06）