Модель TinyLlama/TinyLlama-1.1B-Chat-v1.0 дообученная на датасете cardiffnlp/tweet_eval, задача классификации сентимента твита, вывести одно из трех слов - negative, neutral, positive.

Дообучение

Модель дообучалась при помощи QLoRA.

  • Ранг LoRA = 8
  • QLoRA применялась ко всем весам attention, Q, K, V, O
  • load_in_4bit=True
  • bnb_4bit_quant_type="nf4"
  • bnb_4bit_compute_dtype=torch.float16
  • lora_alpha=4
  • lora_dropout=0.0
  • bias="none"
  • task_type="CAUSAL_LM"
  • num_train_epochs=1
  • per_device_train_batch_size=32
  • gradient_accumulation_steps=1
  • warmup_steps=100
  • group_by_length=True
  • lr_scheduler_type="cosine"
  • fp16=True
  • learning_rate=2e-4
  • weight_decay=1e-3

Метрика на валидации

F1=0.18

image/png

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mcnckc/llm-course-hw3-tinyllama-qlora

Finetuned
(302)
this model

Dataset used to train mcnckc/llm-course-hw3-tinyllama-qlora

Collection including mcnckc/llm-course-hw3-tinyllama-qlora