GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
sjsim
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
sjsim
Model Tree
Qwen/Qwen3-14B
Input Modalities
Output Modalities
Supported Functionality
The goal is to test how far a small, locally-runnable open-source model can be pushed with cheap, lightweight training. Instead of calling a frontier API, can a 14B model that runs on one 16GB consumer GPU be given the reasoning style of a specific expert? That means the way they frame a problem, the priors they argue from, and how they handle uncertainty.
Lee Kuan Yew is a good test case. His reasoning method is distinctive and well-documented, and there is a large public record to learn from. The result is a roughly 1GB adapter, trained overnight on one consumer GPU for a few dollars of API cost, that measurably shifts the base model toward that method (see Evaluation below). The pipeline is a reusable template. Swap the source material and you can teach any well-documented expert's reasoning to a model you own and run offline. It is fully open source.
Research into style transfer and historical-persona modelling, and educational exploration of a reasoning style. Not for impersonation, and not for presenting outputs as authentic statements by the real person.
Judged by claude-opus-4-8 on 24 held-out interview questions that none of the
models trained on. Six reasoning moves, plus a 1 to 5 voice score:
| reasoning move | base Qwen3-14B | this adapter (epoch-2) | epoch-3 |
|---|---|---|---|
| reframes the question | 29% | 38% | 29% |
| reasons from first principles | 50% | 54% | 62% |
| concrete historical analogy | 0% | 25% | 38% |
| interests over sentiment | 75% | 88% |
This is the epoch-2 checkpoint. A fully-trained epoch-3 adapter reached a lower training loss but overfit. On unseen questions it lost half its "bounds its uncertainty" and its question-reframing, because it had memorised his confident, declarative register. Epoch-2 generalises better and ties epoch-3 on voice. Note the eval is n=24, so the smaller per-move numbers are directional.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigimport torchtok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B",quantization_config=BitsAndBytesConfig(load_in_4bit=True,bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),device_map={"": 0})model = PeftModel.from_pretrained(base, "sjsim/lky-qlora")msgs = [{"role": "system", "content": "You are Lee Kuan Yew, Prime Minister of ""Singapore, speaking candidly in an interview. It is August 1965."},{"role": "user", "content": "Will Singapore survive as an independent nation?"},]prompt = tok.apply_chat_template(msgs, tokenize=False,add_generation_prompt=True, enable_thinking=False)ids = tok(prompt, return_tensors="pt").to("cuda")out = model.generate(**ids, max_new_tokens=500, do_sample=True,temperature=0.8, top_p=0.9)print(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True))
Keep enable_thinking=False. The style lives in the visible answer.
| 79% |
| bounds its uncertainty | 8% | 33% | 17% |
| blunt and direct | 46% | 88% | 88% |
| voice (1 to 5) | 2.04 | 2.88 | 2.96 |