GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Yangtze-ailab
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Yangtze-ailab
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
An LDM runs a recurrent generate → select → evaluate → update loop in which an LLM
proposes candidates, a probabilistic surrogate turns observations into a posterior mean and
uncertainty, and an acquisition function selects the next experiment. This model is the
proposer. It differs from the companion
LDM-SFT-Qwen3.5-9B-MixedScience
in one respect: the Gaussian-process values are not shown in the prompt during training,
which forces the acquisition reasoning to be reconstructed from the raw history in natural
language rather than read off surrogate numbers. It emits a chain-of-thought trace followed
by a structured action.
Qwen/Qwen3.5-9Bqwen3_5 (chain-of-thought / thinking enabled)Withholding the surrogate values makes training consistent with deployment, where the acquisition loop exposes no GP numbers to the proposer, and encourages a task-agnostic search intuition that lives in the weights rather than in a numeric input. In practice the acquisition reasoning is barely affected — even when GP values are provided, the reasoning overwhelmingly draws on the observed outcomes (stall length, noise level, best-so-far) rather than on the surrogate numbers.
python
from transformers import AutoModelForCausalLM, AutoTokenizerrepo = "Yangtze-ailab/LDM-CoT-SFT-Qwen3.5-9B-MixedScience"tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="bfloat16", device_map="auto", trust_remote_code=True)messages = [{"role": "system", "content": SYSTEM_PROMPT}, # proposer role + output contract{"role": "user", "content": SEARCH_STATE}, # evaluated history + constraints (no GP values)]inputs = tok.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=True, return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=2048, temperature=0.7)print(tok.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
Full-parameter SFT of Qwen/Qwen3.5-9B (DeepSpeed ZeRO-3 with CPU offload, bf16, gradient
checkpointing), sequence length 16,384, learning rate 1e-5 with a cosine schedule and 0.03
warmup ratio, 2 epochs; framework LLaMA-Factory. Chat template qwen3_5 with thinking
enabled. The reasoning targets are in English.
Released under the MIT license. The base model Qwen/Qwen3.5-9B remains subject to its own license terms.