Ganlen233/Sensor-Material-Expert-Qwen2.5-7B

---

language: - zh - en tags: - materials-science - sensors - qwen - chemistry base_model: Qwen/Qwen2.5-7B

介绍 / Introduction

Sensor-Material-Expert-Qwen2.5-7B 是一款专注于传感器材料领域的专家级大语言模型。该模型基于 Qwen2.5-7B，通过大规模传感器科学文献、材料属性数据及实验报告进行精调（SFT/LoRA），旨在辅助研究人员进行材料筛选、性能预测及机理分析。

Sensor-Material-Expert-Qwen2.5-7B is an expert-level LLM specialized in the field of sensor materials. Based on Qwen2.5-7B, it has been fine-tuned on a large-scale corpus of sensor science literature, material property datasets, and experimental reports, aiming to assist researchers in material screening, performance prediction, and mechanism analysis.

模型特性 / Features

• 领域专业性 (Domain Expertise): 涵盖气体传感器、生物传感器、压力传感器等多种材料体系（如金属氧化物、碳纳米材料、MOFs等）。
• 任务覆盖 (Task Coverage): 支持材料制备工艺推荐、带隙预测建议、传感器响应机理分析等任务。
• 双语支持 (Bilingual): 针对中英文材料科学文献进行了优化。

快速开始 / Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Ganlen233/Sensor-Material-Expert-Qwen2.5-7B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "请解释掺杂对氧化锡（SnO2）基气体传感器在检测甲醛时的灵敏度影响机理。"
messages = [
    {"role": "system", "content": "你是一个材料科学专家，专注于传感器材料的研究。"},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)