llm-hw-3
Collection
Collection of models from the third LLM course homework. It containes three LLMs fine-tuned using LoRA, QLoRA, and DoRA. • 3 items • Updated
Model Card for Model ID
it was used to fine-tune TinyLlama/TinyLlama-1.1B-Chat-v1.0 for tweet tone classification problem. Default model achieved 0.20 f1-score, while fine-tuned version achieved 0.55 f1-score in less than 4 minutes of fine-tuning on a single A100
Prameters
LoRA was used with r=16 and alpha=32 to fine-tune "q_proj", "k_proj", "v_proj", "o_proj", "up_proj", "down_proj".
Training parameters
BATCH_SIZE = 128 LEARNING_RATE = 1e-3 NUM_EPOCHS = 1
Metrics
F1 score is 0.54 on a test set
Examples
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for spankevich/llm-course-hw3-tinyllamma-qlora
Base model
TinyLlama/TinyLlama-1.1B-Chat-v1.0