Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-25 09:19:23 +01:00
Code Issues Packages Projects Releases Wiki Activity

Fix missing bos token for some models (including Llama-3) (#6050)

Browse Source
This commit is contained in:
Belladore 2024-05-27 15:21:30 +03:00 committed by GitHub
parent 8df68b05e9
commit a363cdfca1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
modules/text_generation.py
View File

@ -138,7 +138,19 @@ def encode(prompt, add_special_tokens=True, add_bos_token=True, truncation_lengt
input_ids = np.array(input_ids).reshape(1, len(input_ids))
else:
input_ids = shared.tokenizer.encode(str(prompt), return_tensors='pt', add_special_tokens=add_special_tokens)
if not add_bos_token:
if hasattr(shared.tokenizer, 'bos_token_id'):
if add_bos_token:
if (len(input_ids[0]) > 0 and input_ids[0][0] != shared.tokenizer.bos_token_id) or len(input_ids[0]) == 0:
# Add a missing bos token (it may not have been added due to faulty model metadata)
bos_tensor = torch.tensor([[shared.tokenizer.bos_token_id]])
input_ids = torch.cat((bos_tensor, input_ids), 1)
# Prevent double bos token due to jinja templates with <s> somewhere
while len(input_ids[0]) > 1 and input_ids[0][0] == shared.tokenizer.bos_token_id and input_ids[0][1] == shared.tokenizer.bos_token_id:
input_ids = input_ids[:, 1:]
else:
# Remove any bos token that may have been added
while len(input_ids[0]) > 0 and input_ids[0][0] == shared.tokenizer.bos_token_id:
input_ids = input_ids[:, 1:]