GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
XinyuGuan
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
XinyuGuan
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
adapter_model.safetensors: LoRA adapter weights.adapter_config.json: PEFT adapter configuration, with Qwen/Qwen3.5-9B as the base model reference.tokenizer.json, tokenizer_config.json, chat_template.jinja: tokenizer and chat-format files used during evaluation.train_metrics.json, eval_field_report.json, selection_agreement_n20.json: aggregate training and evaluation summaries.Per-example teacher traces, API credentials, private prompts, and intermediate optimizer states are not included.
bash
hf download XinyuGuan/CICL \--local-dir artifacts/hf_release/cicl-qwen35-qlora-adapter
The adapter is intended for reproducing the CICL surrogate-judge experiments. It should be loaded with the matching Qwen3.5-9B base model through PEFT.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase_id = "Qwen/Qwen3.5-9B"adapter_id = "XinyuGuan/CICL"tokenizer = AutoTokenizer.from_pretrained(adapter_id, trust_remote_code=True)base = AutoModelForCausalLM.from_pretrained(base_id,trust_remote_code=True,device_map="auto",)model = PeftModel.from_pretrained(base, adapter_id)
In the CICL repository, qwen_local defaults to the Hugging Face base model and this adapter:
text
QWEN_LOCAL_BASE=Qwen/Qwen3.5-9BQWEN_LOCAL_ADAPTER=XinyuGuan/CICL
Example preflight command:
bash
python3 -m cicl_agent.evaluation.llm_agreement_preflight \--repo experiments/data/synthetic/v1/repo \--tasks experiments/data/synthetic/v1/tasks.jsonl \--teacher-examples artifacts/outputs/latest/synthetic_opus_v1/llm_examples.clean.jsonl \--llm-provider qwen_local
Example field-level evaluation:
bash
PYTHONPATH=. CUDA_VISIBLE_DEVICES=0 python3 -m training.scripts.eval_qwen_judge \--base Qwen/Qwen3.5-9B \--adapter XinyuGuan/CICL \--val training/data/opus_v1/val.jsonl \--output artifacts/outputs/latest/qwen_local_eval/eval_field_report.json
On the held-out validation split used in the CICL experiments, the adapter produced parseable JSON for all 144 evaluated examples. Mean absolute error was below 0.07 across the five scalar judgment fields reported in eval_field_report.json.
These numbers are intended as diagnostic evidence for the paper's surrogate-judge study. They should not be interpreted as a general-purpose replacement for stronger teacher models.
Qwen/Qwen3.5-9B.