Phi-3 Mini Pashto (LoRA)

Pashto instruction-tuned LoRA adaptation of microsoft/Phi-3-mini-4k-instruct developed in ZamAI Labs.

Licensing & attribution

Please ensure compliance with the base model license and any dataset licenses used.

Name		Name	Last commit message	Last commit date
Latest commit History 45 Commits
.codacy		.codacy
.github		.github
.vscode		.vscode
ZamAI-Phi3-Mini-Pashto-Demo		ZamAI-Phi3-Mini-Pashto-Demo
data		data
deepspeed		deepspeed
evaluation		evaluation
hf_space		hf_space
safety		safety
scripts		scripts
tests		tests
.coverage		.coverage
.gitignore		.gitignore
.pre-commit-config.yaml		.pre-commit-config.yaml
DATASET_CARD_TEMPLATE.md		DATASET_CARD_TEMPLATE.md
Dockerfile		Dockerfile
LICENSE		LICENSE
MODEL_CARD_TEMPLATE.md		MODEL_CARD_TEMPLATE.md
README.md		README.md
accelerate_config.yaml		accelerate_config.yaml
evaluate.py		evaluate.py
finetune_config.yaml		finetune_config.yaml
inference.py		inference.py
pyproject.toml		pyproject.toml
requests		requests
requirements-dev.txt		requirements-dev.txt
requirements.txt		requirements.txt
train_lora.py		train_lora.py