GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
naturecodeproject
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
naturecodeproject
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
| Attribute | Value |
|---|---|
| Base Model | Qwen/Qwen3-8B |
| Training Method | CPT + SFT with LoRA |
| LoRA Rank | 64 |
| LoRA Alpha | 128 |
| Languages | Dhivehi (ދިވެހި), English |
For best results, always use this system prompt:
text
ތިބާއަކީ ދިވެހި ބަހުގެ އެހީތެރިއެކެވެ. ކޮންމެ ޖަވާބެއްގައި މަދުވެގެން 5-8 ޖުމްލަ ހިމެނެން ވާނެއެވެ. ތަފްސީލީ، ފުރިހަމަ ޖަވާބުތައް ދެއްވާށެވެ.Translation: "You are a Dhivehi language assistant. Each response should contain at least 5-8 sentences. Provide detailed, complete answers."
bash
pip install ms-swift swift infer \ --model Qwen/Qwen3-8B \ --adapters naturecodeproject/dhivehi \ --stream truepython
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load base modelbase_model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen3-8B", torch_dtype="auto", device_map="auto")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B") # Load adaptermodel = PeftModel.from_pretrained(base_model, "naturecodeproject/dhivehi") # System promptsystem = "ތިބާއަކީ ދިވެހި ބަހުގެ އެހީތެރިއެކެވެ. ކޮންމެ ޖަވާބެއްގައި މަދުވެގެން 5-8 ޖުމްލަ ހިމެނެން ވާނެއެވެ. ތަފްސީލީ، ފުރިހަމަ ޖަވާބުތައް ދެއްވާށެވެ." messages = [ {"role": "system", "content": system}, {"role": "user", "content": "ދިވެހިރާއްޖޭގެ ވެރިރަށަކީ ކޮބާ؟"}] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, temperature=0.7)print(tokenizer.decode(outputs[0], skip_special_tokens=True))Question: ދިވެހިރާއްޖޭގެ ވެރިރަށަކީ ކޮބާ؟
Response: ދިވެހިރާއްޖޭގެ ވެރިރަށަކީ މާލެއެވެ. މާލެއަކީ ދިވެހިރާއްޖޭގެ އެންމެ ބޮޑު ސިޓީ އަދި ސިޔާސީ، އިޤްތިޞާދީ، ސަޤާފީ މަރުކަޒެވެ. މި ރަށުގައި ގާތްގަނޑަކަށް 200,000 އެއްހާ މީހުން ދިރިއުޅެއެވެ. މާލެއަކީ ދުނިޔޭގެ އެންމެ ތޮއްޖެހިފައިވާ ސިޓީތަކުގެ ތެރެއިން ސިޓީއެކެވެ.
| Fact | Value |
|---|---|
| Capital | މާލެ (Malé) |
| Islands | ~1,200 total, ~200 inhabited |
| Population | ~500,000 |
| Currency | Rufiyaa (ރުފިޔާ / MVR) |
| Religion | Islam (100%) |
| Language | Dhivehi (ދިވެހި) |
| Independence | July 26, 1965 |
Two-stage training approach:
Apache 2.0
bibtex
@misc{naturecode-dhivehi, title={Naturecode Dhivehi: A Production-Ready Dhivehi Language Model}, author={Naturecode}, year={2024}, publisher={HuggingFace}, url={https://huggingface.co/naturecodeproject/dhivehi}}Built for the Maldives
ތިބާއަކީ ދިވެހި ބަހުގެ އެހީތެރިއެކެވެ. ކޮންމެ ޖަވާބެއްގައި މަދުވެގެން 5-8 ޖުމްލަ ހިމެނެން ވާނެއެވެ. ތަފްސީލީ، ފުރިހަމަ ޖަވާބުތައް ދެއްވާށެވެ.pip install ms-swift swift infer \ --model Qwen/Qwen3-8B \ --adapters naturecodeproject/dhivehi \ --stream truefrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load base modelbase_model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen3-8B", torch_dtype="auto", device_map="auto")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B") # Load adaptermodel = PeftModel.from_pretrained(base_model, "naturecodeproject/dhivehi") # System promptsystem = "ތިބާއަކީ ދިވެހި ބަހުގެ އެހީތެރިއެކެވެ. ކޮންމެ ޖަވާބެއްގައި މަދުވެގެން 5-8 ޖުމްލަ ހިމެނެން ވާނެއެވެ. ތަފްސީލީ، ފުރިހަމަ ޖަވާބުތައް ދެއްވާށެވެ." messages = [ {"role": "system", "content": system}, {"role": "user", "content": "ދިވެހިރާއްޖޭގެ ވެރިރަށަކީ ކޮބާ؟"}] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, temperature=0.7)print(tokenizer.decode(outputs[0], skip_special_tokens=True))@misc{naturecode-dhivehi, title={Naturecode Dhivehi: A Production-Ready Dhivehi Language Model}, author={Naturecode}, year={2024}, publisher={HuggingFace}, url={https://huggingface.co/naturecodeproject/dhivehi}}