Update README.md

README.md

@@ -1,3 +1,73 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- zh
+- en
+tags:
+- qwen
+- sales
+- unsloth
+- lora
+- logic-tuning
+- strategic-thinking
+---
+
+---
+
+# QiMing(启明)
+
+### 重新定义了逻辑的AI,只为更智能.
+### An AI that rewrites its own rules for greater intelligence.
+
+---
+
+### 感谢mradermacher制作的gguf版本
+
+https://huggingface.co/mradermacher/QiMing-Plus-v1-GGUF
+
+https://huggingface.co/mradermacher/QiMing-Plus-v1-i1-GGUF
+
+---
+
+# 如何使用
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model_name = "aifeifei798/QiMing-Plus-v1"
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+# parsing thinking content
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+print("thinking content:", thinking_content) # no opening <think> tag
+print("content:", content)
+```
+
+