oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-11 01:23:40 +00:00
Code Issues Projects Releases Packages Wiki Activity

Lint

Browse source
This commit is contained in:
oobabooga 2024-02-13 16:05:41 -08:00
parent 193548edce
commit 069ed7c6ef
2 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

8
modules/llama_cpp_python_hijack.py
View file

@ -36,7 +36,7 @@ def eval_with_progress(self, tokens: Sequence[int]):
progress_bar = range(0, len(tokens), self.n_batch)
for i in progress_bar:
batch = tokens[i : min(len(tokens), i + self.n_batch)]
batch = tokens[i: min(len(tokens), i + self.n_batch)]
n_past = self.n_tokens
n_tokens = len(batch)
self._batch.set_batch(
@ -44,16 +44,16 @@ def eval_with_progress(self, tokens: Sequence[int]):
)
self._ctx.decode(self._batch)
# Save tokens
self.input_ids[n_past : n_past + n_tokens] = batch
self.input_ids[n_past: n_past + n_tokens] = batch
# Save logits
rows = n_tokens
cols = self._n_vocab
offset = (
0 if self.context_params.logits_all else n_tokens - 1
) # NOTE: Only save the last token logits if logits_all is False
self.scores[n_past + offset : n_past + n_tokens, :].reshape(-1)[
self.scores[n_past + offset: n_past + n_tokens, :].reshape(-1)[
:
] = self._ctx.get_logits()[offset * cols : rows * cols]
] = self._ctx.get_logits()[offset * cols: rows * cols]
# Update n_tokens
self.n_tokens += n_tokens