Update README.md

README.md

@@ -43,10 +43,27 @@ Specifically, Mistral-7B-0.1 is used as the base model, with 16 experts and 4 ex
 - Spider: 8,659 samples
 - codefuse-ai/Evol-Instruction-66k: 100%, 66,862 samples
 
-Alpaca Prompt Format
+## Alpaca Prompt Format
 
 ```
 ### Instruction:
 <instruction>
 ### Response:
-```
+```
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name_or_path="uukuguy/speechless-sparsetral-16x7b-MoE"
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=True).eval()
+
+system = ""Below is an instruction that describes a task.\nWrite a response that appropriately completes the request.\n\n""
+prompt = f"{system}\n\n### Instruction:\n{instruction}\n\n### Response:"
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+pred = model.generate(**inputs, max_length=4096, do_sample=True, top_k=50, top_p=0.99, temperature=0.9, num_return_sequences=1)
+print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
+```