Downloads · 30 days
25
28% of all-time downloads
tam-omani-v3
shaaarplegs/tam-omani-v3
tam-omani-v3 is a text generation model from shaaarplegs. Use it when you need the model to write or continue text. It is set up for peft.
LoRA/QLoRA adapter for Tam (تم) — an Omani-Arabic assistant by Direction AI, fine-tuned on cleaned Omani-culture behaviour data. Apply on top of Qwen/Qwen3-14B:
All-time downloads
90
Public
Repo size
525 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors514 MB · 98%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026
- SHA
- 048b2d13
Try a prompt
Base models
Model card
From the Hugging Face model README
tam-omani-v3
LoRA/QLoRA adapter for Tam (تم) — an Omani-Arabic assistant by Direction AI, fine-tuned on
cleaned Omani-culture behaviour data. Apply on top of Qwen/Qwen3-14B:
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = "Qwen/Qwen3-14B"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(model, "shaaarplegs/tam-omani-v3")
- Task
- Text Generation
- Library
- peft
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026