Update README.md

README.md

@@ -60,19 +60,21 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, AutoProcessor
 import torch
 import numpy as np
 
+hf_model = "bytedance-research/ChatTS-14B"
 # Load the model, tokenizer and processor
-model = AutoModelForCausalLM.from_pretrained("./ckpt", trust_remote_code=True, device_map="auto", torch_dtype='float16')
-tokenizer = AutoTokenizer.from_pretrained("./ckpt", trust_remote_code=True)
-processor = AutoProcessor.from_pretrained("./ckpt", trust_remote_code=True, tokenizer=tokenizer)
+# For pre-Ampere GPUs (like V100) use `_attn_implementation='eager'`
+model = AutoModelForCausalLM.from_pretrained(hf_model, trust_remote_code=True, device_map="auto", torch_dtype='float16')
+tokenizer = AutoTokenizer.from_pretrained(hf_model, trust_remote_code=True)
+processor = AutoProcessor.from_pretrained(hf_model, trust_remote_code=True, tokenizer=tokenizer)
 # Create time series and prompts
 timeseries = np.sin(np.arange(256) / 10) * 5.0
 timeseries[100:] -= 10.0
 prompt = f"I have a time series length of 256: <ts><ts/>. Please analyze the local changes in this time series."
 # Apply Chat Template
-prompt = f"<|im_start|>system
+prompt = f"""<|im_start|>system
 You are a helpful assistant.<|im_end|><|im_start|>user
 {prompt}<|im_end|><|im_start|>assistant
-"
+"""
 # Convert to tensor
 inputs = processor(text=[prompt], timeseries=[timeseries], padding=True, return_tensors="pt")
 # Model Generate