Closed cyLi-Tiger closed 7 months ago
This seems to be an issue with the original LLaMA2-Chat encountering NaN. What was your input?
This seems to be an issue with the original LLaMA2-Chat encountering NaN. What was your input?
Simply "Hello". @Liyuhui-12
I can run this code normally. Did you use the correct weights for LLaMA2-Chat? It should be meta-llama/Llama-2-7b-chat-hf instead of meta-llama/Llama-2-7b-chat.
I got the tree shape wrong, my bad. Thanks!
What was wrong with your original tree shape @cyLi-Tiger? I am facing a similar issue
Great work!
I tried your example for llama-7b-chat and changed the tree structure in choices.py into
baseline = [[0], [0, 0], [0, 0, 0], [0, 0, 0, 0]]
to simulate speculative decoding without token tree, and got the error above. Any clues?log attached: