Update README.md

README.md

@@ -30,9 +30,10 @@ import torch
 from transformers import LlamaForCausalLM, LlamaTokenizer
 
 # the previewed version of OpenAlpaca
-model_path = r'openllmplayground/openalpaca_7b_700bt_preview' 
+model_path = r'openllmplayground/openalpaca_7b_700bt_preview'
 tokenizer = LlamaTokenizer.from_pretrained(model_path)
 model = LlamaForCausalLM.from_pretrained(model_path).cuda()
+tokenizer.bos_token_id, tokenizer.eos_token_id = 1,2 # see https://github.com/openlm-research/open_llama#preview-weights-release-and-usage
 
 # same prompt as provided in https://crfm.stanford.edu/2023/03/13/alpaca.html
 instruction = r'What is an alpaca? How is it different from a llama?'
@@ -42,16 +43,15 @@ instruction = r'What is the capital of Tanzania?'
 instruction = r'Write a well-thought out abstract for a machine learning paper that proves that 42 is the optimal seed for training neural networks.'
 '''
 
-prompt_no_input = r'### Instruction:\n{instruction}\n\n### Response:'
+prompt_no_input = f'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:'
 tokens = tokenizer.encode(prompt_no_input)
-bos_token_id, eos_token_id = 1, 2 # see https://github.com/openlm-research/open_llama#preview-weights-release-and-usage
-tokens = [bos_token_id] + tokens + [eos_token_id] + [bos_token_id]
-tokens = torch.LongTensor(tokens[-1024:]).unsqueeze(0).cuda()
+
+tokens = torch.LongTensor(tokens).unsqueeze(0)
 instance = {'input_ids': tokens,
-            'top_k': 50,
-            'top_p': 0.9,
-            'generate_len': 128}
-            
+                    'top_k': 50,
+                    'top_p': 0.9,
+                    'generate_len': 128}
+                    
 length = len(tokens[0])
 with torch.no_grad():
     rest = model.generate(
@@ -62,14 +62,12 @@ with torch.no_grad():
             top_p=instance['top_p'], 
             top_k=instance['top_k']
         )
-
+        
 output = rest[0][length:]
-string = tokenizer.decode(output, skip_special_tokens=False)
-string = string.replace('<s>', '').replace('</s>', '').strip()
+string = tokenizer.decode(output, skip_special_tokens=True)
 print(f'[!] Generation results: {string}')
 ```
 
-
 # License and Usage
 
 OpenAlpaca is permissively licensed under the Apache 2.0 license and can be used freely for academic/commercial purposes.