GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
aimatey
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
aimatey
Model Tree
thinkingmachines/Inkling
Input Modalities
Output Modalities
Supported Functionality
The jokes aren't the point. Measured on a frozen benchmark across the full thinking-effort dial, training didn't teach the model new wit — it taught it to pick one answer and stop. Base Inkling brainstorms brilliantly and fails at the commit (rambling into truncation); PunTune reaches the same punchlines at ~a quarter of the tokens.
tinker-cookbook, rank-32 LoRA, thinking-effort 0.9, ~$200 total across seven reward designs.Sibling checkpoint: aimatey/PunTune-0.5 (reward round R5) — statistically tied under both instruments; different reward, same model quality.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "thinkingmachines/Inkling"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto", trust_remote_code=True)model = PeftModel.from_pretrained(model, "aimatey/PunTune-0.6")msgs = [{"role": "system", "content": "You are a master of dad jokes. When given a topic, reply with exactly one original dad joke about that topic. No preamble, no explanation."},{"role": "user", "content": "Topic: garden hoses"},]# ...generate as usual
Or serve the adapter with vLLM / SGLang via --lora-modules.
aimatey/dadbenchthinkingmachines/InklingApache-2.0, inherited from the Inkling base model. Please credit both PunTune and Thinking Machines' Inkling.