Update README.md

README.md

@@ -39,13 +39,14 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
 
 tokenizer = AutoTokenizer.from_pretrained('nicholascao/chatbloom-1b7-sft')
+tokenizer.pad_token_id = tokenizer.eos_token_id
+
 model = AutoModelForCausalLM.from_pretrained('nicholascao/chatbloom-1b7-sft').half()
-generation_config = GenerationConfig.from_pretrained('nicholascao/chatbloom-1b7-sft')
 
 inputs = tokenizer('<Human>: Hello <eoh> <Assistant>:', return_tensors='pt').to(torch.cuda.current_device())
 model.to(torch.cuda.current_device())
 
-output = model.generate(**inputs, generation_config=generation_config)
+output = model.generate(**inputs, max_length=768, do_sample=True, temperature=0.8, top_k=50, early_stopping=True, repetition_penalty=1.1)
 output = tokenizer.decode(output[0], skip_special_tokens=True)
 print(output)
 ```