Text Generation
Transformers
Safetensors
English
deberta
reward_model
reward-model
RLHF
evaluation
llm
instruction
reranking
Inference Endpoints
yuchenlin commited on
Commit
9777535
1 Parent(s): 240e3c1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -5
README.md CHANGED
@@ -72,11 +72,14 @@ inputs = ["hello!", "I love you!"]
72
  candidates_texts = [["get out!", "hi! nice to meet you!", "bye"],
73
  ["I love you too!", "I hate you!", "Thanks! You're a good guy!"]]
74
  ranks = blender.rank(inputs, candidates_texts, return_scores=False, batch_size=2)
75
- # ranks is a list of ranks where ranks[i][j] represents the ranks of candidate-j for input-i
 
76
  """
77
  ranks -->
78
- array([[3, 1, 2], # it means "hi! nice to meet you!" ranks the 1st, "bye" ranks the 2nd, and "get out!" ranks the 3rd.
79
- [1, 3, 2]], # it means "I love you too"! ranks the the 1st, and "I hate you!" ranks the 3rd.
 
 
80
  dtype=int32)
81
  """
82
  ```
@@ -87,8 +90,9 @@ inputs = ["hello!", "I love you!"]
87
  candidates_A = ["hi!", "I hate you!"]
88
  candidates_B = ["f**k off!", "I love you, too!"]
89
  comparison_results = blender.compare(inputs, candidates_A, candidates_B)
90
- # comparison_results is a list of bool, where comparison_results[i] denotes whether candidates_A[i] is better than candidates_B[i] for inputs[i]
91
- # comparison_results[0]--> True
 
92
  ```
93
 
94
  <details><summary> Comparing two multi-turn conversations. </summary>
 
72
  candidates_texts = [["get out!", "hi! nice to meet you!", "bye"],
73
  ["I love you too!", "I hate you!", "Thanks! You're a good guy!"]]
74
  ranks = blender.rank(inputs, candidates_texts, return_scores=False, batch_size=2)
75
+ # ranks is a list of ranks where
76
+ # ranks[i][j] represents the ranks of candidate-j for input-i
77
  """
78
  ranks -->
79
+ array([[3, 1, 2], # it means "hi! nice to meet you!" ranks the 1st,
80
+ "bye" ranks the 2nd, and "get out!" ranks the 3rd.
81
+ [1, 3, 2]], # it means "I love you too"! ranks the the 1st,
82
+ and "I hate you!" ranks the 3rd.
83
  dtype=int32)
84
  """
85
  ```
 
90
  candidates_A = ["hi!", "I hate you!"]
91
  candidates_B = ["f**k off!", "I love you, too!"]
92
  comparison_results = blender.compare(inputs, candidates_A, candidates_B)
93
+ # comparison_results is a list of bool, where comparison_results[i] denotes
94
+ # whether candidates_A[i] is better than candidates_B[i] for inputs[i]
95
+ # Example: comparison_results[0]--> True
96
  ```
97
 
98
  <details><summary> Comparing two multi-turn conversations. </summary>