You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Can you provide a script similar to inference-example.py, that utilises run_generation.py file? i.e instead of command like execution python src/run_generation.py --model_type llama --model_name_or_path meta-llama/Llama-2-13b-chat-hf \ --prefix "<s>[INST] <<SYS>>\n You are a helpful assistant. Answer with detailed responses according to the entire instruction or question. \n<</SYS>>\n\n Summarize the following book: " \ --prompt example_inputs/harry_potter_full.txt \ --suffix " [/INST]" --test_unlimiformer --fp16 --length 200 --layer_begin 16 \ --index_devices 1 --datastore_device 1
instead load the model and run inference from python script.
Thanks in advance!
The text was updated successfully, but these errors were encountered:
Can you provide a script similar to
inference-example.py
, that utilisesrun_generation.py
file? i.e instead of command like executionpython src/run_generation.py --model_type llama --model_name_or_path meta-llama/Llama-2-13b-chat-hf \ --prefix "<s>[INST] <<SYS>>\n You are a helpful assistant. Answer with detailed responses according to the entire instruction or question. \n<</SYS>>\n\n Summarize the following book: " \ --prompt example_inputs/harry_potter_full.txt \ --suffix " [/INST]" --test_unlimiformer --fp16 --length 200 --layer_begin 16 \ --index_devices 1 --datastore_device 1
instead load the model and run inference from python script.
Thanks in advance!
The text was updated successfully, but these errors were encountered: