Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix wrong special tokens being used for llmlingua-2 #182

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix wrong special tokens being used for llmlingua-2 #182

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c8709e6
Fix(LLMLingua-2): fix wrong special tokens being used (#181)
cornzz Sep 13, 2024
518204d
Adjust llmlingua-2 tests after switching to correct special tokens
cornzz Sep 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions llmlingua/prompt_compressor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2161,7 +2161,7 @@ def __get_context_prob(
chunk_list.append(c)

dataset = TokenClfDataset(
chunk_list, tokenizer=self.tokenizer, max_len=self.max_seq_len
chunk_list, tokenizer=self.tokenizer, max_len=self.max_seq_len, model_name=self.model_name
)
dataloader = DataLoader(
dataset, batch_size=self.max_batch_size, shuffle=False, drop_last=False
Expand Down Expand Up @@ -2339,7 +2339,7 @@ def split_string_to_words(input_string):
chunk_list.append(c)

dataset = TokenClfDataset(
chunk_list, tokenizer=self.tokenizer, max_len=self.max_seq_len
chunk_list, tokenizer=self.tokenizer, max_len=self.max_seq_len, model_name=self.model_name
)
dataloader = DataLoader(
dataset, batch_size=self.max_batch_size, shuffle=False, drop_last=False
Expand Down
Loading