GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
mondk
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
mondk
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Trained from random initialization on a modest amount of data with limited compute — a small educational project, not a production-quality assistant. Expect reliable chat formatting but limited/inconsistent knowledge and occasional incoherent answers.
markdown
<|user|>{your message}<|assistant|>
The model stops generating at <|end|>.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchmodel = AutoModelForCausalLM.from_pretrained("mondk/Safetensors.msh-tiny")tokenizer = AutoTokenizer.from_pretrained("mondk/Safetensors.msh-tiny")prompt = "<|user|>\nhi\n<|assistant|>\n"input_ids = tokenizer(prompt, return_tensors="pt").input_idsoutput = model.generate(input_ids, max_new_tokens=100, do_sample=True, temperature=0.8, top_k=40)print(tokenizer.decode(output[0][input_ids.shape[1]:], skip_special_tokens=True))
Combining 3 well-known open instruction/chat datasets plus a small hand-written set of everyday chit-chat (greetings, thanks, small talk):
tatsu-lab/alpacateknium/OpenHermes-2.5HuggingFaceH4/no_robots