GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
roskosmos19
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
roskosmos19
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Faster • Cheaper • Stronger for agentic & coding tasks
Optimized successor of the original Rhea-4B-Coding / Athenea line.
| Aspect | Original multi-pass Rhea | Rhea-4B-Agentic (this) |
|---|---|---|
| Reasoning style | Forced 3-pass (implement→review→final) | Single-pass + optional <think> |
| Context | 262k | 32 768 (covers real agent workloads) |
| Forced long outputs | min_new_tokens=1024 | Removed – answers as long as needed |
| Special tokens | Broken prefixes + many vision | Clean + lean (tools + thinking only) |
| Generation defaults | High temp / long forced | Tuned 0.4 / 0.9 for quality + speed |
| Agentic readiness | Good | Improved tool-calling template |
| Inference cost (VRAM/time) | Higher (long forced reasoning) | Significantly lower |
→ Same 4B base intelligence, noticeably faster and cheaper to run, better real-world agentic behavior because it is no longer forced into three full generations.
<think>...</think> for chain-of-thought (optional, model decides when useful)<|im_start|>, <|im_end|>, <think>, </think>, tool tagsjson
{"temperature": 0.4,"top_p": 0.9,"top_k": 30,"repetition_penalty": 1.05,"max_new_tokens": 8192}
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_name = "./Rhea-4B-Agentic"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name,torch_dtype="auto",device_map="auto")messages = [{"role": "user", "content": "Write a secure Python function that validates JWT tokens and handles expiration gracefully."}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=2048)print(tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=False))
--max-model-len 32768Apache 2.0