Update app.py

app.py

@@ -1,10 +1,15 @@
-from transformers import AutoTokenizer, AutoModelForCausalLM
-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))
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+model_name = "deepseek-ai/deepseek-math-7b-base"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
+model.generation_config = GenerationConfig.from_pretrained(model_name)
+model.generation_config.pad_token_id = model.generation_config.eos_token_id
+
+text = "The integral of x^2 from 0 to 2 is"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs.to(model.device), max_new_tokens=100)
+
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(result)