GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Neobe
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Neobe
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
| Benchmark | chrF | chrF++ | BLEU |
|---|---|---|---|
| gold (human references, article-level, N=500) | 49.34 | 41.11 | 4.12 |
| held-out chunk (in-distribution) | 67.17 | 59.98 | 20.87 |
| held-out sentence (in-distribution) | 60.58 | 53.54 | 15.91 |
chrF is the metric to trust for Thaana; BLEU is unreliable (word segmentation / morphology).
Input (en): While this is a 7.6 percent increase compared to the same period last year, an average of 7,778 tourists visit the Maldives daily.
Output (dv): މިއީ، ވޭތުވެދިޔަ އަހަރުގެ މި މުއްދަތާ ބަލާއިރު 7.6 ޕަސެންޓުގެ ކުރިއެރުމެއް ކަމަށްވާއިރު، ދުވާލަކު އެވްރެޖްކޮށް 7،778 ފަތުރުވެރިން ރާއްޖެ ޒިޔާރަތްކުރެއެވެ.
Real held-out sample and this model's own output.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base, adapter = "Qwen/Qwen3-4B", "Neobe/en-dhivehi-qwen3-4b-lora-sentence"tok = AutoTokenizer.from_pretrained(adapter)model = PeftModel.from_pretrained( AutoModelForCausalLM.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="cuda"), adapter).eval() src = "The President of the Maldives met with the cabinet today."msgs = [{"role":"user","content": "Translate the following English text to Dhivehi. Output only the translation, " f"no explanations.\n\nEnglish: {src}\nDhivehi:"}]prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)inp = tok(prompt, return_tensors="pt", truncation=True, max_length=3072).to("cuda")out = model.generate(**inp, max_new_tokens=1024, num_beams=1, repetition_penalty=1.15, no_repeat_ngram_size=0, length_penalty=1.0, do_sample=False)print(tok.decode(out[0][inp["input_ids"].shape[1]:], skip_special_tokens=True))~9–10 GB VRAM (bf16). Qwen tokenizes Thaana at ~1.8 tokens/char — don't over-truncate the input.
Base Qwen/Qwen3-4B; LoRA r=16, α=32, targets q/k/v/o+gate/up/down; bf16; adamw_torch LR 2e-4 cosine; max_length 1536; 1 epoch; effective batch ~32; gradient checkpointing.
Domain = Maldivian news / press / Wikipedia; technical or informal English is out of distribution. Non-human references are machine-generated (distillation).
bibtex
@misc{neobe_en_dhivehi_qwen3_4b_lora_sentence_2026, title = {Qwen3-4B English→Dhivehi (sentence-level)}, author = {Neobe}, year = {2026}, howpublished = {\url{https://huggingface.co/Neobe/en-dhivehi-qwen3-4b-lora-sentence}}}import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base, adapter = "Qwen/Qwen3-4B", "Neobe/en-dhivehi-qwen3-4b-lora-sentence"tok = AutoTokenizer.from_pretrained(adapter)model = PeftModel.from_pretrained( AutoModelForCausalLM.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="cuda"), adapter).eval() src = "The President of the Maldives met with the cabinet today."msgs = [{"role":"user","content": "Translate the following English text to Dhivehi. Output only the translation, " f"no explanations.\n\nEnglish: {src}\nDhivehi:"}]prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)inp = tok(prompt, return_tensors="pt", truncation=True, max_length=3072).to("cuda")out = model.generate(**inp, max_new_tokens=1024, num_beams=1, repetition_penalty=1.15, no_repeat_ngram_size=0, length_penalty=1.0, do_sample=False)print(tok.decode(out[0][inp["input_ids"].shape[1]:], skip_special_tokens=True))@misc{neobe_en_dhivehi_qwen3_4b_lora_sentence_2026, title = {Qwen3-4B English→Dhivehi (sentence-level)}, author = {Neobe}, year = {2026}, howpublished = {\url{https://huggingface.co/Neobe/en-dhivehi-qwen3-4b-lora-sentence}}}