GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
dedyirama
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
dedyirama
Model Tree
unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit
Input Modalities
Output Modalities
Supported Functionality
| Base model | unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit, a 4-bit build of Qwen/Qwen2.5-1.5B-Instruct |
| Method | QLoRA (4-bit NF4 with double quantization); LoRA r=16, alpha=16, dropout 0, on q/k/v/o_proj and gate/up/down_proj |
| Weights | LoRA adapter merged into the base model and saved in float16 (~3.1 GB) |
| Chat format | ChatML (<|im_start|> / <|im_end|>), with no default system prompt |
| Language | Indonesian |
| License | Apache 2.0, inherited from the base model |
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "dedyirama/qwen2.5-1.5b-indonesian-qlora"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto") messages = [{"role": "user", "content": "Jelaskan secara singkat apa itu energi terbarukan."}]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt").to(model.device) outputs = model.generate(inputs, max_new_tokens=256, repetition_penalty=1.1)print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))The model also loads with Unsloth's FastLanguageModel.from_pretrained(..., load_in_4bit=True), which is how the RAG notebook runs it on a T4 GPU.
| Data | Ichsan2895/alpaca-gpt4-indonesian: 49,969 single-turn pairs reformatted from FreedomIntelligence/alpaca-gpt4-indonesian (CC BY-SA 4.0), split 95/5 into train (47,470) and validation (2,499) with seed 3407 |
| Formatting | Each pair mapped to a ChatML user/assistant conversation |
| Trainer | TRL SFTTrainer via Unsloth, no sequence packing, max sequence length 2,048 |
| Schedule | 800 steps (~0.13 epoch), effective batch size 8 (2 × 4 gradient accumulation), learning rate 2e-4, linear decay, 50 warmup steps |
| Optimizer | adamw_8bit, weight decay 0.01, fp16 |
| Hardware | One NVIDIA Tesla T4 (Google Colab) |
Two configurations were trained with the same schedule, and the one with the lower validation loss was published:
| Run | LoRA r / alpha | Learning rate | Trainable params | Final validation loss |
|---|---|---|---|---|
| This model | 16 / 16 | 2e-4 | 18.5M (1.18%) | 1.3726 |
| Alternative | 32 / 32 | 1e-4 | 36.9M (2.34%) | 1.3784 |
Each configuration was trained only once, and rank and learning rate were changed together, so the small gap does not show that either setting is better. Validation loss is the only metric reported: the model was not evaluated on downstream benchmarks or compared against the base model.
Qwen/Qwen2.5-1.5B-Instruct.from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "dedyirama/qwen2.5-1.5b-indonesian-qlora"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto") messages = [{"role": "user", "content": "Jelaskan secara singkat apa itu energi terbarukan."}]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt").to(model.device) outputs = model.generate(inputs, max_new_tokens=256, repetition_penalty=1.1)print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))