GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
greta44
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
greta44
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Generate short Albanian orthography exercise proposals, for example:
missing_letter — plotëso shkronjënfind_error — gjej gabiminexplain_error — shpjego gabimin (pedagogjikisht)bash
pip install torch transformers peft accelerate sentencepiecepython
import jsonimport torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer ADAPTER_ID = "greta44/albanian-spelling-lora"BASE_MODEL = "Qwen/Qwen2.5-0.5B-Instruct" tokenizer = AutoTokenizer.from_pretrained(ADAPTER_ID, use_fast=True)if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token model = AutoModelForCausalLM.from_pretrained(BASE_MODEL)model = PeftModel.from_pretrained(model, ADAPTER_ID)model.eval() device = "cuda" if torch.cuda.is_available() else "cpu"model.to(device) seed_word = "mirë"grade = 3exercise_type = "missing_letter" # or: find_error, explain_error payload = { "seed_word": seed_word, "grade": grade, "difficulty": "easy", "exercise_type": exercise_type, "safety": "Kthe vetëm propozim; përgjigjja finale kontrollohet nga rregullat.",} prompt = ( "### Instruksion:\n" f"Gjenero një ushtrim të sigurt për drejtshkrimin shqip. Kategoria: {exercise_type}. " f"Klasa: {grade}. Vështirësia: easy. Fjala bazë: {seed_word}.\n\n" "### Input:\n" + json.dumps(payload, ensure_ascii=False) + "\n\n### Përgjigje:\n") inputs = tokenizer(prompt, return_tensors="pt").to(device)with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=120, temperature=0.4, top_p=0.9, do_sample=True, pad_token_id=tokenizer.eos_token_id, ) text = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)print(text.strip())bash
python generate_exercises.py \ --adapter greta44/albanian-spelling-lora \ --seed-word mirë \ --grade 3 \ --type missing_letter| Item | Value |
|---|---|
| Train / eval split | 686 / 77 (from 763 AlbLingo exercises, seed=42) |
| LoRA rank / alpha / dropout | 16 / 32 / 0.05 |
| Target modules | q_proj, k_proj, v_proj, o_proj |
| Max length | 256 |
| Effective batch size | 4 |
| Hardware | Apple M1 (MPS, float32) |
| Protocol target |
See training_manifest.json in this repository for the full measured summary, and training_loss.png for the loss curve.
adapter_model.safetensors + adapter_config.json — LoRA weightstokenizer* / vocab.json / merges.json — tokenizer filesgenerate_exercises.py — standalone demo scripttraining_manifest.json — hyperparameters + measured metricstraining_loss.png — training loss curveinstruction_dataset.jsonl — sample instruction pairsIf you use this model, please cite the related PhD research on Albanian educational NLP / AlbLingo and link this repository.
Apache 2.0
| 3 epochs |
| Reported run | instrumented Phase A + Phase B continuation (~1.4 epoch-equivalent) |
| Train loss | 3.149 → min 0.276 |
| Held-out eval_loss | 0.345 |
| Approx. wall-clock | ~62 minutes (logged span) |