Qwen3-4B Hadis Fine-tune

Qwen3-4B modelinin hadis verileriyle fine-tune edilmiş Türkçe/Arapça versiyonu.

Model Hakkında

Base model: Qwen3-4B
Eğitim verisi: 138.789 hadis çifti
Eğitim yöntemi: QLoRA (4-bit)
Eğitim süresi: ~17 dakika (L40S)

Kullanım

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="omuralcin/qwen3-hadis",
    load_in_4bit=True,
)

GGUF Versiyonu

omuralcin/qwen3-hadis-gguf

Notlar

Loss: 0.33 (stabil)
Packing aktif, verimli eğitim

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 omuralcin/qwen3-hadis

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

unsloth/Qwen3-4B

Adapter

(48)

this model