nsomazr's picture
Add model card with 3B evaluation results
4dff451 verified
|
Raw
History Blame Contribute Delete
1.46 kB
metadata
language:
  - en
  - sw
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
  - blood-donation
  - tanzania
  - swahili
  - bilingual
  - medical
  - unsloth
  - lora

Blood Donation Advisory β€” Llama 3.2 3B (LoRA Adapters)

Bilingual (English + Kiswahili) blood donation advisor fine-tuned for Tanzania.

Evaluation Results β€” Llama 3.2 3B

NLP Quality (higher is better)

Metric Llama 3.2 1B Llama 3.2 3B Winner
ROUGE-1 0.4060 0.4410 3B βœ…
ROUGE-2 0.1845 0.2639 3B βœ…
ROUGE-L 0.3039 0.3619 3B βœ…
BLEU 0.2134 0.2461 3B βœ…
BERTScore Precision 0.8741 0.8817 3B βœ…
BERTScore Recall 0.8628 0.8676 3B βœ…
BERTScore F1 0.8683 0.8744 3B βœ…
Perplexity ↓ 3.89 3.25 3B βœ…

Efficiency

Metric Llama 3.2 1B Llama 3.2 3B
Training time (min) 10.42 22.13
Peak VRAM (GB) 10.83 11.113
LoRA VRAM (GB) 9.738 8.361

System Prompt

You are a helpful blood donation advisor serving Tanzania.
Always respond in the same language the user writes in.

Quick Start (LoRA Adapters)

from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="nsomazr/blood-donation-llama32-3b-lora",
    max_seq_length=8192, dtype=None, load_in_4bit=True,
)