qwen25-1.5b-imx93-lora

Qwen2.5-1.5B Fine-tuned for i.MX93 SoC | i.MX93 专用微调模型

模型简介 | Model Description

基于 Qwen2.5-1.5B-Instruct 微调的 i.MX93 SoC 技术文档专用模型。擅长回答寄存器配置、引脚复用、时钟设置等技术问题。

Fine-tuned Qwen2.5-1.5B-Instruct model specialized for NXP i.MX93 SoC technical documentation. Expert in register configuration, pin multiplexing, clock settings, and technical Q&A.

使用方法 | Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("NXPKEN/qwen25-1.5b-imx93-lora")
model = AutoModelForCausalLM.from_pretrained("NXPKEN/qwen25-1.5b-imx93-lora", torch_dtype=torch.float16, device_map="auto")

messages = [{"role": "system", "content": "You are an i.MX93 SoC expert."}, {"role": "user", "content": "如何配置 LPUART3？"}]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.2)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

专业领域 | Specialties

• GPIO 配置和引脚复用 | GPIO configuration and pin multiplexing
• UART/SPI/I2C 通信设置 | Communication interfaces setup
• 时钟系统配置 | Clock system configuration
• 寄存器位字段解释 | Register bit field explanations

训练信息 | Training Info

• 方法 | Method: LoRA (Low-Rank Adaptation)
• 环境 | Environment: Windows 11 + RTX 2000 Ada (8GB)
• 数据 | Data: i.MX93 技术问答数据集

许可证 | License

Apache 2.0