Text2Text Generation
Transformers
PyTorch
English
t5
text-generation-inference
Inference Endpoints
nreimers commited on
Commit
453aa73
1 Parent(s): 48f4974

update readme

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -47,6 +47,8 @@ for i in range(len(outputs)):
47
  print(f'{i + 1}: {query}')
48
  ```
49
 
 
 
50
  ## Training
51
  This model fine-tuned [google/t5-v1_1-base](https://huggingface.co/google/t5-v1_1-base) for 575k training steps. For the training script, see the `train_script.py` in this repository.
52
 
@@ -64,7 +66,7 @@ The datasets include besides others:
64
 
65
  ## Prefix
66
 
67
- This model was trained **with prefixed**: You start the text with a specific index that defines what type out output text you would like to receive. Depending on the prefix, the output is different.
68
 
69
  E.g. the above text about Python produces the following output:
70
 
 
47
  print(f'{i + 1}: {query}')
48
  ```
49
 
50
+ **Note:** `model.generate()` is non-deterministic. It produces different queries each time you run it.
51
+
52
  ## Training
53
  This model fine-tuned [google/t5-v1_1-base](https://huggingface.co/google/t5-v1_1-base) for 575k training steps. For the training script, see the `train_script.py` in this repository.
54
 
 
66
 
67
  ## Prefix
68
 
69
+ This model was trained **with a prefix**: You start the text with a specific index that defines what type out output text you would like to receive. Depending on the prefix, the output is different.
70
 
71
  E.g. the above text about Python produces the following output:
72