Torch import was missing on line 120 (#5)

- Torch import was missing on line 120 (20b71b6b4019294147020b9770784d014a19ba8f)


Co-authored-by: Yucel <[email protected]>

README.md

@@ -117,6 +117,7 @@ You may also construct the pipeline from the loaded model and tokenizer yourself
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
 model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3"  # either local folder or huggingface model name
 # Important: The prompt needs to be in the same format the model was trained with.