emnlp 2023 commited on
Commit
88caff7
·
1 Parent(s): 151eadf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -10
README.md CHANGED
@@ -70,23 +70,19 @@ Additionally to conventional generation, using Tool-augmented generation require
70
  (1) implementation of the tool(s) and
71
  (2) a customization of generate() method augmenting input context on-demand with the outputs of the tools.
72
 
73
- You can find these two components implemented in the attached **gadgets/gadget_assisted_model.py** and **gadgets/gadget.py** in this model's repo
74
  and the project's [home repo](https://github.com/emnlp2023sub/gadgets).
75
 
76
  After adding these two scripts to your directory, you can use the model as follows:
77
 
78
  ```python
79
- from gadget_assisted_model import GadgetAssistedModel
80
- from gadget import Calculator
81
 
82
  from transformers import T5ForConditionalGeneration, T5Tokenizer
83
 
 
 
84
 
85
- class GadgetAssistedT5(GadgetAssistedModel, T5ForConditionalGeneration):
86
- # GadgetAssistedModel overrides the standard generate() from transformers
87
- pass
88
-
89
-
90
  model = GadgetAssistedT5.from_pretrained("emnlp2023/calc-flan-xl")
91
  tokenizer = T5Tokenizer.from_pretrained("emnlp2023/calc-flan-xl")
92
 
@@ -106,8 +102,10 @@ tokenizer.decode(output_ids[0], spaces_between_special_tokens=False)
106
  ```
107
  This returns:
108
  ```html
109
- According to the ratio, Mike got 2/5*$2500 = $<gadget id="calculator">2/5*2500</gadget><output>1_000</output> 1000
110
- Mike will have $1000-$200 = $<gadget id="calculator">1000-200</gadget><output>800</output> 800 after buying a shirt.
 
 
111
  Final result is<result>800</result></s>
112
  ```
113
 
 
70
  (1) implementation of the tool(s) and
71
  (2) a customization of generate() method augmenting input context on-demand with the outputs of the tools.
72
 
73
+ You can find these two components implemented in the attached **gadgets/model.py** and **gadgets/gadget.py** in this model's repo
74
  and the project's [home repo](https://github.com/emnlp2023sub/gadgets).
75
 
76
  After adding these two scripts to your directory, you can use the model as follows:
77
 
78
  ```python
 
 
79
 
80
  from transformers import T5ForConditionalGeneration, T5Tokenizer
81
 
82
+ from gadgets.model import gadget_assisted_model
83
+ from gadgets.gadget import Calculator
84
 
85
+ GadgetAssistedT5 = gadget_assisted_model(T5ForConditionalGeneration)
 
 
 
 
86
  model = GadgetAssistedT5.from_pretrained("emnlp2023/calc-flan-xl")
87
  tokenizer = T5Tokenizer.from_pretrained("emnlp2023/calc-flan-xl")
88
 
 
102
  ```
103
  This returns:
104
  ```html
105
+ According to the ratio, for every 5 parts that Johnson gets, Mike gets 2 parts Since Johnson got $2500,
106
+ each part is therefore $2500/5 = $<gadget id="calculator">2500/5</gadget><output>500</output> 500
107
+ Mike will get 2*$500 = $<gadget id="calculator">2*500</gadget><output>1_000</output> 1000
108
+ After buying the shirt he will have $1000-$200 = $<gadget id="calculator">1000-200</gadget><output>800</output> 800 left.
109
  Final result is<result>800</result></s>
110
  ```
111