GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
M1n1A1
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
M1n1A1
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
Lower is better. These are language-modelling losses from the CPT run, not benchmark scores.
| Split | Loss |
|---|---|
| English | 1.7632 |
| BCMS Ijekavian | 2.0607 |
| Serbian Ekavian | 2.2962 |
| Foundation | Qwen3.5-4B (post-trained; not Qwen3.5-4B-Base) |
| Stage | Serbian continued pretraining (CPT) |
| Training tokens | 50M-token Serbian pilot mix |
| Precision | bf16 safetensors (~8.7 GB) |
| Context | 262,144 tokens in the config; trained at 2,048 |
| SFT / DPO | Not included |
| Languages | English, Serbian, Croatian, Bosnian |
The tokenizer and chat template are inherited from Qwen3.5-4B, but this checkpoint has not been instruction-tuned. It will autocomplete; it will not reliably follow instructions or hold a chat persona.
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "M1n1A1/MiniAI-Quata2-4b-v0.2-base"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto") prompt = "Beograd je glavni grad"inputs = tok(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=64)print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))For a chat model, use the SFT release. For a fine-tune, start here and add your own SFT data.
Apache 2.0, inherited from Qwen3.5-4B.
bibtex
@misc{miniai2026quata2v02base, title = {MiniAI Quata2 4B v0.2 base}, author = {{MiniAI}}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/M1n1A1/MiniAI-Quata2-4b-v0.2-base}}, note = {Serbian CPT checkpoint before SFT; base model Qwen3.5-4B}}Base model:
bibtex
@misc{qwen3_5_4b, title = {Qwen3.5-4B}, author = {{Qwen Team}}, year = {2026}, howpublished = {\url{https://huggingface.co/Qwen/Qwen3.5-4B}}}from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "M1n1A1/MiniAI-Quata2-4b-v0.2-base"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto") prompt = "Beograd je glavni grad"inputs = tok(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=64)print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))@misc{miniai2026quata2v02base, title = {MiniAI Quata2 4B v0.2 base}, author = {{MiniAI}}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/M1n1A1/MiniAI-Quata2-4b-v0.2-base}}, note = {Serbian CPT checkpoint before SFT; base model Qwen3.5-4B}}@misc{qwen3_5_4b, title = {Qwen3.5-4B}, author = {{Qwen Team}}, year = {2026}, howpublished = {\url{https://huggingface.co/Qwen/Qwen3.5-4B}}}