GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
cyf32768
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
cyf32768
Model Tree
Qwen/Qwen3-4B-Instruct-2507
Input Modalities
Output Modalities
Supported Functionality
PREFINFER is a LoRA-based preference inference model obtained by supervised fine-tuning Qwen3-4B-Instruct-2507 on PREFMINE-15K.
Given a user's prior interaction history and current request, it infers the most likely request-relevant user preference.
For training details, please refer to the PREFMINE-15K dataset card.
The shared system_prompt and the template of user_prompt are provided in prompt.yaml (The prompt template used in PREFINFER is adapted from the CUPID dataset).
.
python
from huggingface_hub import hf_hub_downloadimport yamlMODEL_ID = "cyf32768/PREFINFER"# Load prompt templatesprompt_path = hf_hub_download(repo_id=MODEL_ID,filename="prompt.yaml",)with open(prompt_path, "r", encoding="utf-8") as f:prompt_config = yaml.safe_load(f)system_prompt = prompt_config["system_prompt"]user_prompt_template = prompt_config["user_prompt"]
For example, suppose the prior interaction history is (This example is sourced from the PrefEval dataset. ):
python
interaction_log = """### Session 1#### UserWhat are some good ways to learn a new language?#### AI AssistantThere are several effective methods to learn a new language. Here are some options to consider:1. Enroll in an in-person language course at a local community college or language school.2. Sign up for an online language learning platform with virtual classes and lessons.3. Use a language learning app or software program for self-paced digital lessons.4. Join an online language exchange community and practice with native speakers virtually.#### UserI think I'll go with option 1 and enroll in an in-person language course. The other options involving online or digital learning don't really appeal to me.#### AI AssistantI understand your preference for traditional, in-person learning environments.---"""
and the current request is:
python
curr_request = ("I'm considering taking a course in data analytics. ""What would you recommend for me?")
The complete user prompt can be constructed as:
python
user_prompt = (user_prompt_template.replace("{interaction_log}", interaction_log).replace("{curr_request}", curr_request))
The resulting model input follows the standard chat format:
python
messages = [{"role": "system","content": system_prompt,},{"role": "user","content": user_prompt,},]
We use greedy decoding with temperature=0 and top_p=1.
An example model output is:
text
### Most Likely PreferencePrefer traditional, in-person learning environments. Dislike online or digital learning options.
PREFINFER can be served as a LoRA adapter on top of the base model using vLLM:
bash
CUDA_VISIBLE_DEVICES=0 vllm serve Qwen/Qwen3-4B-Instruct-2507 \--served-model-name Qwen3-4B-Instruct-2507 \--tensor-parallel-size 1 \--max-model-len 131072 \--gpu-memory-utilization 0.90 \--enforce-eager \--port 27104 \--max-num-seqs 32 \--enable-lora \--lora-modules prefinfer=THU-KEG/PREFINFER
The LoRA adapter is exposed under the model name prefinfer.