Instructions to use yushan7kokomi/SilverCareAI-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yushan7kokomi/SilverCareAI-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="yushan7kokomi/SilverCareAI-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yushan7kokomi/SilverCareAI-7B")
model = AutoModelForCausalLM.from_pretrained("yushan7kokomi/SilverCareAI-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yushan7kokomi/SilverCareAI-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yushan7kokomi/SilverCareAI-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yushan7kokomi/SilverCareAI-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yushan7kokomi/SilverCareAI-7B

SGLang

How to use yushan7kokomi/SilverCareAI-7B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "yushan7kokomi/SilverCareAI-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yushan7kokomi/SilverCareAI-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "yushan7kokomi/SilverCareAI-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yushan7kokomi/SilverCareAI-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yushan7kokomi/SilverCareAI-7B with Docker Model Runner:
```
docker model run hf.co/yushan7kokomi/SilverCareAI-7B
```

SilverCareAI-7B

SilverCareAI-7B 是一个基于 deepseek-ai/DeepSeek-R1-Distill-Qwen-7B 的中文医疗对话模型，专为老年人健康评估与慢病管理场景设计。模型使用 Huatuo26M-Lite 中的问诊数据进行微调，具备输出规范医疗建议、风险分析与健康评分的能力。用于本人大创项目《智护银龄》，分享出来旨在交流学习。

🧠 模型特色

🔍 精调于老年健康问诊场景，关注高血压、糖尿病、心脏病等慢病管理
📊 可根据自然语言问题生成诊疗建议
💡 基于 Qwen 7B distilled 模型，推理高效，资源占用小

🧪 使用示例

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("yushan7kokomi/SilverCareAI-7B", device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("yushan7kokomi/SilverCareAI-7B")

prompt = "请根据以下描述判断健康状况：患者，女，72岁，长期患有糖尿病，近一个月血糖控制不佳，空腹血糖为8.5mmol/L，伴有乏力与视力模糊。"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

🧑‍🏫 微调参数

微调工具：LLaMA-Factory (llamafactory-cli)

微调方式：LoRA（adapter 插入）

模板格式：deepseekr1

数据集：Huatuo26M-Lite

模型基座：deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

训练设备：NVIDIA RTX 4090 x 1

数据最大样本数：100,000 条

epoch 数：2

最大输入长度：1024

batch size：2（梯度累计 steps=16）

优化器：adamw_torch

学习率：2e-5

学习率调度器：cosine

LoRA 参数：

rank: 8

alpha: 32

dropout: 0.05

target: all

使用 bf16 精度训练

验证集比例：1%

每 1000 步保存与评估一次

🛠 模型用途

本模型可用于以下任务：

老年人健康状况分析

医疗问诊助手对话生成

健康评分与风险评估生成

医疗自然语言理解与生成研究

🚫 使用限制

本模型仅供研究与非商业用途使用，不具备医疗诊断资质，禁止用于实际临床决策支持系统。使用者需遵守 Apache-2.0 开源协议及相关法律法规。

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for yushan7kokomi/SilverCareAI-7B

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Adapter

(122)

this model

Adapters

2 models

yushan7kokomi
/

SilverCareAI-7B