GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
PixelSpaceAI
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
PixelSpaceAI
Model Tree
mesolitica/Malaysian-Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This adapter changes how the model talks, not what it knows. That distinction is the whole story of this project.
For factual accuracy, pair this adapter with retrieval (RAG). In our tests, grounding generation on a retrieved AWS doc chunk fixed the fact errors while this adapter kept the Malay voice. Use the adapter for tone, use retrieval for truth.
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerBASE = "mesolitica/Malaysian-Qwen2.5-7B-Instruct"tok = AutoTokenizer.from_pretrained(BASE)model = AutoModelForCausalLM.from_pretrained(BASE, dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(model, "PixelSpaceAI/Malaysian-Qwen2.5-7B-AWS-Malay-LoRA")msgs = [{"role": "user", "content": "Apakah perbezaan antara Amazon S3 Standard dan S3 Glacier?"}]inputs = tok.apply_chat_template(msgs, add_generation_prompt=True,return_tensors="pt", return_dict=True).to(model.device)out = model.generate(**inputs, max_new_tokens=400, do_sample=False)print(tok.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
mesolitica/Malaysian-Qwen2.5-7B-Instruct (Qwen chat template)r=16, alpha=32, dropout=0.05, target modules
q,k,v,o,gate,up,down. lr 2e-4, cosine, batch 2 × grad-accum 4, max_length=1024,
gradient checkpointing, assistant_only_loss=True.load_best_model_at_end; eval loss floors at epoch 2 (best checkpoint shipped).Adapter only (~161 MB). Requires the base model at inference.
This adapter builds directly on the work of others:
mesolitica/Malaysian-Qwen2.5-7B-Instruct
by Mesolitica — a continue-finetune on ~1.5B tokens of curated Malaysian instruction data.Qwen/Qwen2.5-7B-Instruct by Alibaba (Qwen team), Apache-2.0.All credit for the underlying Malay language capability belongs to Mesolitica and the Qwen team; this repo only adds a small task-specific LoRA adapter on top.
License note: this repo is tagged Apache-2.0 by inheritance from Qwen2.5-7B-Instruct. Mesolitica's intermediate model does not state an explicit license on its model page; if you require licensing certainty for the base weights, confirm directly with Mesolitica.