Text Generation
Transformers
PyTorch
Safetensors
English
llama
finance
text-generation-inference
AdaptLLM commited on
Commit
6699e7b
·
1 Parent(s): fe15cf6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -57,7 +57,7 @@ MMM Chicago Stock Exchange, Inc.
57
  Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?'''
58
 
59
  # We use the prompt template of LLaMA-2-Chat demo
60
- prompt = f"<s>[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n{user_input} [/INST]"
61
 
62
  inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
63
  outputs = model.generate(input_ids=inputs, max_length=4096)[0]
 
57
  Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?'''
58
 
59
  # We use the prompt template of LLaMA-2-Chat demo
60
+ prompt = f"<s>[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n{user_input} [/INST]"
61
 
62
  inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
63
  outputs = model.generate(input_ids=inputs, max_length=4096)[0]