武汉理工大学网络中心 · 智能大模型服务平台
校内服务文本对话、问答、推理等场景
Qwen3.5-35B-A3B
35B参数级别的高性能语言模型,支持复杂推理任务和多轮对话
Qwen3.5-27B
27B参数的中型语言模型,平衡了性能和效率
Qwen3.5-122B-A10B
122B参数超大规模语言模型,支持最复杂的推理和多轮对话
Qwen3.6-35B-A3B
35B参数级别的MoE架构高性能语言模型,激活参数仅3B,兼具高推理效率与强大的逻辑推理能力
文本嵌入、语音识别等场景
bge-m3
多功能文本嵌入模型,支持多语言、长文本和检索增强生成 (RAG)
whisper-1
高精度语音识别模型,支持多语种语音转文本
import requests
url = "http://218.197.140.7:3001/v1/chat/completions"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer YOUR_LOCAL_TOKEN"
}
payload = {
"model": "Qwen3.5-35B-A3B",
"messages": [{"role": "user", "content": "你好,请介绍一下你"}],
"max_tokens": 500
}
response = requests.post(url, headers=headers, json=payload)
print(response.json())import requests
url = "http://218.197.140.7:3001/v1/embeddings"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer YOUR_LOCAL_TOKEN"
}
payload = {
"model": "bge-m3",
"input": ["你好,这是一次测试"]
}
response = requests.post(url, headers=headers, json=payload)
data = response.json()
print("向量维度:", len(data["data"][0]["embedding"]))| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| model | string | 是 | 模型名称 |
| messages | array | 是 | 对话消息列表(仅 Chat 接口) |
| input | array | 是 | 需要嵌入的文本列表(仅 Embedding 接口) |
| max_tokens | integer | 否 | 最大生成长度 |
| temperature | float | 否 | 采样温度 (0-2),默认 0.7 |
{
"id": "chatcmpl-xxx",
"object": "chat.completion",
"created": 1234567890,
"model": "Qwen3.5-35B-A3B",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "这里是回答内容"
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 100,
"completion_tokens": 50,
"total_tokens": 150
}
}{
"object": "list",
"data": [{
"object": "embedding",
"embedding": [0.123, -0.456, ...],
"index": 0
}],
"model": "bge-m3",
"usage": {
"prompt_tokens": 2,
"total_tokens": 2
}
}