Files
hebei-tourism-deepseek/README.md
ModelHub XC 0a2e69ec22 初始化项目,由ModelHub XC社区提供模型
Model: jinvbar/hebei-tourism-deepseek
Source: Original Platform
2026-08-06 03:44:13 +08:00

56 lines
1.5 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
license: apache-2.0
tags:
- transformers
- safetensors
- llama
- hebei-tourism
- deepseek
tasks:
- text-generation
- hebei-tourism
- deepseek
widgets:
- enable: true
version: 1
task: text-generation
inputs:
- type: text
displayType: TextArea
name: input_text
validator:
max_words: 128
displayProps:
label: 输入文本
placeholder: 请输入要处理的文本,例如‘推荐河北的旅游景点’
output:
displayType: Text
displayValueMapping: text
examples:
- inputs:
- data: 推荐河北的旅游景点
- inputs:
- data: 河北有哪些历史文化名城
---
# 河北旅游DeepSeek 模型
这是一个基于 `deepseek-ai/deepseek-coder-6.7b-base` 微调的文本生成模型,专门用于推荐河北旅游相关的景点、文化名城等。
## 模型用途
- **模型框架**`transformers` 库,支持文本生成。
- **支持任务**:文本生成(`text-generation`)。
## 使用方法
你可以使用 `transformers` 库加载模型:
```python
from modelscope import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("jinvbar/hebei-tourism-deepseek")
tokenizer = AutoTokenizer.from_pretrained("jinvbar/hebei-tourism-deepseek")
input_text = "介绍一下河北的旅游景点"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))