[ot][spam][crazy] Quickly autotranscribing xkcd 4/1 correctly
Undiscussed Horrific Abuse, One Victim of Many
gmkarl at gmail.com
Sat Apr 2 05:05:59 PDT 2022
Here's the snippet around greedy generation:
# 10. run greedy search
return self.greedy_search(
input_ids,
logits_processor=logits_processor,
stopping_criteria=stopping_criteria,
pad_token_id=pad_token_id,
eos_token_id=eos_token_id,
output_scores=output_scores,
return_dict_in_generate=return_dict_in_generate,
synced_gpus=synced_gpus,
**model_kwargs,
)
Then:
print(inspect.getsource(s2t.model.greedy_search))
This chunk is inside a while True loop, and is what's of interest:
# forward pass to get next token
outputs = self(
**model_inputs,
return_dict=True,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
)
...
next_token_logits = outputs.logits[:, -1, :]
this plane of "logits" is the log probabilities the model is guessing
as coming next, for every token in its vocabulary.
More information about the cypherpunks
mailing list