Update README.md

README.md

@@ -1,11 +1,52 @@
-# my-qwen2.5-tangshi-ollama-model
+---
+language:
+- zh
+license: apache-2.0
+base_model: Qwen/Qwen2.5-0.5B
+pipeline_tag: text-generation
+tags:
+- 唐诗
+- 古诗生成
+- chinese-poetry
+- qwen2.5
+---
 
-Ollama model wrapper pointing to the GGUF produced from `my-qwen2.5-tangshi-model`.
+# Tangshi｜中文唐诗生成模型
+基于Qwen2.5-0.5B微调的古诗专用大模型，擅长自动生成五言/七言绝句、律诗，专为古典诗词创作优化。训练数据为57000首唐诗全参数。
 
-Modelfile:
+## 仓库信息
+Huggingface地址：`Emaoso/Tangshi`
+包含两类权重：
+1. `model.safetensors`：原生transformers权重，用于Python代码调用
+2. `model-ollama.gguf`：GGUF量化权重，用于Ollama本地部署
+附带：Ollama一键构建配置 Modelfile
 
-```
-FROM ../my-qwen2.5-tangshi-model/Model-494M-F16.gguf
-```
+## 一、Python Transformers调用（推荐）
+### 1.安装依赖
+```bash
+pip install torch transformers
 
-Place this folder under Ollama's models directory or use `ollama pull` / `ollama import` as needed.
+
+====================================
+代码示例
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_name = "Emaoso/Tangshi"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# 写诗指令
+prompt = "写一首春日五言绝句"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=80)
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# 清洗多余注释
+import re
+result = re.sub(r'（.*|〖.*|见卷.*','',result)
+print(result)
+
+======================================
+ollama 使用
+ollama create tangshi https://huggingface.co/Emaoso/Tangshi/resolve/main/Modelfile
+ollama run tangshi