Downloads · 30 days
6
14% of all-time downloads
qwen3-4b_15k_v0
younesAbaaoud/qwen3-4b_15k_v0
qwen3-4b_15k_v0 is a machine learning model from younesAbaaoud. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
Modele fine-tune sur Qwen/Qwen3-4B-Instruct-2507 pour le dialecte marocain (Darija).
All-time downloads
42
Public
Repo size
144 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors132 MB · 92%
At a glance
- Library
- peft
- Access
- Public
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026
- SHA
- c594cd4e
Base models
Model card
From the Hugging Face model README
Darija Qwen2.5-1.5B — LoRA Adapter
Modele fine-tune sur Qwen/Qwen3-4B-Instruct-2507 pour le dialecte marocain (Darija).
Dataset
- MBZUAI-Paris/Darija-SFT-Mixture
- 500 samples selectionnes et nettoyes (MAX_TOKENS=512, MAX_LATIN_RATIO=0.6)
Configuration LoRA
- lora_rank: 8
- lora_alpha: 16
- lora_dropout: 0.05
- lora_target: all
Utilisation
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507", torch_dtype=torch.float16, device_map="auto")
model = PeftModel.from_pretrained(base, "darija_qwen_lora_adapter")
tokenizer = AutoTokenizer.from_pretrained("darija_qwen_lora_adapter")
- Library
- peft
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026