Update README.md (#2)

- Update README.md (f8a3bcc90c8f7eeceae25bbe8983e4c87d71fd5c)


Co-authored-by: sixgod <[email protected]>

README.md

@@ -49,7 +49,44 @@ We evaluated the GLM-4-9B base model on some typical tasks, and the results are
 
 **This repository is the base version of GLM-4-9B, supporting 8K context length.**
 
-For more inference code and requirements, please visit our [github page](https://github.com/THUDM/GLM-4).
+
+## Quick Start
+
+**For more inference code and requirements, please visit our [github page](https://github.com/THUDM/GLM-4).**
+
+**Please strictly follow the [dependencies](https://github.com/THUDM/GLM-4/blob/main/basic_demo/requirements.txt) to
+install, otherwise it will not run properly**
+
+### Transformers Lib(4.46.0 and later version) for inference:
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import os
+
+os.environ['CUDA_VISIBLE_DEVICES'] = '0' # Set the GPU number. If a single machine has a single card, specify one. If a single machine has multiple cards, specify multiple GPU numbers.
+
+MODEL_PATH = "THUDM/glm-4-9b-hf"
+
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_PATH,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True,
+    device_map="auto"
+).eval()
+device = "cuda" if torch.cuda.is_available() else "cpu"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, trust_remote_code=True)
+
+encoding = tokenizer("what is your name?<|endoftext|>")
+inputs = {key: torch.tensor([value]).to(device) for key, value in encoding.items()}
+
+gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
+with torch.no_grad():
+    outputs = model.generate(**inputs, **gen_kwargs)
+    outputs = outputs[:, inputs['input_ids'].shape[1]:]
+    print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 
 ## LICENSE