GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
xysera
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
xysera
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Property | Value |
|---|---|
| Model family | Zen |
| Scale | Approximately 4B parameters |
| Architecture | Decoder-only causal language model |
| Weight format | BF16 safetensors |
| Primary language | English |
| Primary focus | Structured reasoning and instruction following |
| Release status | Public research release |
Zen 4B was developed using a proprietary model optimization and adaptation pipeline, incorporating iterative training, checkpoint-based evaluation, and targeted refinement to improve reasoning, instruction following, and structured problem-solving capabilities.
Internal evaluation used 500 examples each from ARC-Easy, HellaSwag, PIQA, and Winogrande. Scores use normalized accuracy where available.
| Task | Score |
|---|---|
| ARC-Easy | 68.6% |
| HellaSwag | 61.8% |
| PIQA | 78.8% |
| Winogrande | 73.6% |
These are directional internal results, not leaderboard submissions. They should not be compared directly with results using different prompts, shot counts, sample sizes, or evaluation harnesses.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "xysera/zen-4b"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto")messages = [{"role": "user", "content": "Explain how a binary search works."}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)print(tokenizer.decode(outputs[0], skip_special_tokens=True))The original base checkpoint, QLoRA adapter, intermediate checkpoints, optimizer state, tokenizer, and training logs remain preserved in Xysera's private checkpoint storage. This repository is a clean release repository and does not replace those artifacts.
Zen 4B is an active public research release.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "xysera/zen-4b"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto")messages = [{"role": "user", "content": "Explain how a binary search works."}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)print(tokenizer.decode(outputs[0], skip_special_tokens=True))