Update app.py

app.py

@@ -1,19 +1,10 @@
 from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
-tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
-input_text = """<｜fim▁begin｜>def quick_sort(arr):
-    if len(arr) <= 1:
-        return arr
-    pivot = arr[0]
-    left = []
-    right = []
-<｜fim▁hole｜>
-        if arr[i] < pivot:
-            left.append(arr[i])
-        else:
-            right.append(arr[i])
-    return quick_sort(left) + [pivot] + quick_sort(right)<｜fim▁end｜>"""
-inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_length=128)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True)[len(input_text):])
+tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-1.3b-instruct", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-1.3b-instruct", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
+messages=[
+    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
+]
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+# tokenizer.eos_token_id is the id of <|EOT|> token
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))