Downloads · 30 days
14
9% of all-time downloads
Yusiko/Khazri
Khazri is a machine learning model from Yusiko. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gpl-3.0.
A lightweight, efficient, and fully custom Azerbaijani language model designed for text generation, chat applications, education, and research. Khazri is trained from scratch using a custom 10M-sample Azerbaijani data…
Downloads · 30 days
14
9% of all-time downloads
All-time downloads
149
Public
Parameters
47.7M
337 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors191 MB · 99%
From the Hugging Face model README
A lightweight, efficient, and fully custom Azerbaijani language model designed for text generation, chat applications, education, and research. Khazri is trained from scratch using a custom 10M-sample Azerbaijani dataset and optimized for running on consumer GPUs while maintaining competitive performance.
| Version | Parameters | Type | Context Length | Notes |
|---|---|---|---|---|
| Khazri-36M | ~36.6M | GPT-2 Small variant | 1024 | Higher quality |
Architecture:
Khazri is trained on a 10 million-sample Azerbaijani dataset including:
Preprocessing:
epochs = 1
batch_size = 32
gradient_accumulation = 4
learning_rate = 3e-4
warmup_steps = 500
weight_decay = 0.1
sequence_length = 512
optimizer = AdamW
precision = bf16
Small models saturate VRAM bandwidth → ~4.2 it/s
Solution: shrink model size, adjust batch/accumulation, optimize data loading
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Yusiko/Khazri")
model = AutoModelForCausalLM.from_pretrained("Yusiko/Khazri")
Available at: https://huggingface.co/Yusiko/Khazri
GPL 3.0 License
Created by Yusiko
GitHub: Yusiko99
Website: https://yusi.xo.je
Hugging Face: Yusiko