Torch import was missing on line 120

#5
by Speedsy - opened
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -117,6 +117,7 @@ You may also construct the pipeline from the loaded model and tokenizer yourself
117
 
118
  ```python
119
  from transformers import AutoModelForCausalLM, AutoTokenizer
 
120
 
121
  model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3" # either local folder or huggingface model name
122
  # Important: The prompt needs to be in the same format the model was trained with.
 
117
 
118
  ```python
119
  from transformers import AutoModelForCausalLM, AutoTokenizer
120
+ import torch
121
 
122
  model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3" # either local folder or huggingface model name
123
  # Important: The prompt needs to be in the same format the model was trained with.