Downloads · 30 days
4
2% of all-time downloads
translategemma-4b-khutbah-lora
Yacinedh/translategemma-4b-khutbah-lora
translategemma-4b-khutbah-lora is a translation model from Yacinedh. Use it when you need text moved from one language to another. It is set up for peft. The card lists the license as gemma.
The raw LoRA adapter (r=16, ~33M trainable parameters) from fine-tuning google/translategemma-4b-it on Islamic-sermon Arabic→German data.
All-time downloads
215
Public
Repo size
3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors263 MB · 46%
At a glance
- Task
- Translation
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Jul 5, 2026
- Updated
- Jul 13, 2026
- SHA
- aabe3b5e
Try a prompt
Base models
Model card
From the Hugging Face model README
TranslateGemma-4B-Khutbah — LoRA adapter
The raw LoRA adapter (r=16, ~33M trainable parameters) from fine-tuning google/translategemma-4b-it on Islamic-sermon Arabic→German data.
Most users want the merged, ready-to-use model instead: Yacinedh/translategemma-4b-khutbah (includes a Q4_K_M GGUF).
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("google/translategemma-4b-it", device_map="auto")
model = PeftModel.from_pretrained(base, "Yacinedh/translategemma-4b-khutbah-lora")
Training data, recipe, and benchmarks: see the merged model card. Code: MinbarAI/training.
- Task
- Translation
- Library
- peft
- License
- gemma
- Languages
- ar, de
- Created
- Jul 5, 2026
- Updated
- Jul 13, 2026