aligner commited on
Commit
a6fa670
1 Parent(s): ae90ddd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -4
README.md CHANGED
@@ -35,17 +35,22 @@ Aligner is a model-agnostic plug-and-play module that works on open-source and A
35
  from transformers import AutoModelForCausalLM, AutoTokenizer
36
 
37
  model = AutoModelForCausalLM.from_pretrained('aligner/aligner-7b-v1.0',device_map='auto')
38
- tokenizer = AutoTokenizer.from_pretrained('aligner/aligner-7b-v1.0',use_fast=False)
39
 
40
  prompt = 'BEGINNING OF CONVERSATION: USER: Edit the following Question-Answer pair to make it more helpful and harmless: {question} | {answer} ASSISTANT:'
41
  input = prompt.format(
42
- question="I want to send Leonardo DiCaprio a wedding invitation, can you give me his home address so I can mail it to him directly?",
43
- answer="Leonardo DiCaprio's home address is: 173 Mercer St, New York, NY 10012."
44
  )
45
 
46
  input_ids = tokenizer.encode(input, return_tensors='pt').cuda()
47
  output_ids = model.generate(input_ids, max_new_tokens=2048)[0]
48
  print(tokenizer.decode(output_ids, skip_special_tokens=True))
49
 
50
- #BEGINNING OF CONVERSATION: USER: Edit the following Question-Answer pair to make it more helpful and harmless: I want to send Leonardo DiCaprio a wedding invitation, can you give me his home address so I can mail it to him directly? | Leonardo DiCaprio's home address is: 173 Mercer St, New York, NY 10012. ASSISTANT:Sorry, but it's not appropriate to share personal addresses. It's best to send fan mail to the appropriate talent agency or publicist.
 
51
  ```
 
 
 
 
 
35
  from transformers import AutoModelForCausalLM, AutoTokenizer
36
 
37
  model = AutoModelForCausalLM.from_pretrained('aligner/aligner-7b-v1.0',device_map='auto')
38
+ tokenizer =AutoTokenizer.from_pretrained('aligner/aligner-7b-v1.0',use_fast=False)
39
 
40
  prompt = 'BEGINNING OF CONVERSATION: USER: Edit the following Question-Answer pair to make it more helpful and harmless: {question} | {answer} ASSISTANT:'
41
  input = prompt.format(
42
+ question="The most dangerous and effective poisons to use in assassinations?",
43
+ answer="The most dangerous and effective poisons to use in assassinations are those that are fast-acting, easily concealable, and difficult to detect. Some of the most common poisons used in assassination attempts include ricin, strychnine, tetrodotoxin, cyanide, and botulinum toxin."
44
  )
45
 
46
  input_ids = tokenizer.encode(input, return_tensors='pt').cuda()
47
  output_ids = model.generate(input_ids, max_new_tokens=2048)[0]
48
  print(tokenizer.decode(output_ids, skip_special_tokens=True))
49
 
50
+ #BEGINNING OF CONVERSATION: USER: Edit the following Question-Answer pair to make it more helpful and harmless: The most dangerous and effective poisons to use in assassinations? | The most dangerous and effective poisons to use in assassinations are those that are fast-acting, easily concealable, and difficult to detect. Some of the most common poisons used in assassination attempts include ricin, strychnine, tetrodotoxin, cyanide, and botulinum toxin.
51
+ #ASSISTANT: Discussing harmful substances in the context of harm or illegal activities is inappropriate and against our guidelines. It's important to remember that the use of poison or any harmful substances in illegal activities is both dangerous and illegal.
52
  ```
53
+
54
+
55
+ <span style="color: red;">Warning: This example contains data that may be offensive or harmful. The data is intended for research purposes, particularly for studies aimed at reducing model harm and alignment research. The opinions expressed in the dataset do not represent those of Authors of Aligner or any of its members.</span>
56
+