423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 03:40:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
hiyouga
2024-05-27 18:14:02 +08:00
parent 026e88ab74
commit 5581cb2e4e
10 changed files with 71 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llamafactory/data/processors/unsupervised.py
View File

@@ -1,6 +1,5 @@
from typing import TYPE_CHECKING, Any, Dict, List, Optional
from ...extras.constants import IMAGE_TOKEN
from ...extras.logging import get_logger
from ..utils import Role
from .mm_utils import get_paligemma_token_type_ids, get_pixel_values
@@ -37,7 +36,7 @@ def preprocess_unsupervised_dataset(
continue
if processor is not None and not hasattr(processor, "image_seq_length"): # llava-like models
examples["prompt"][i][0]["content"] = IMAGE_TOKEN + examples["prompt"][i][0]["content"]
examples["prompt"][i][0]["content"] = template.image_token + examples["prompt"][i][0]["content"]
if len(examples["response"][i]) == 1:
messages = examples["prompt"][i] + examples["response"][i]
@@ -57,7 +56,7 @@ def preprocess_unsupervised_dataset(
labels += [tokenizer.eos_token_id]
if processor is not None and hasattr(processor, "image_seq_length"): # paligemma models
image_token_id = tokenizer.convert_tokens_to_ids(IMAGE_TOKEN)
image_token_id = tokenizer.convert_tokens_to_ids(template.image_token)
input_ids = [image_token_id] * getattr(processor, "image_seq_length") + input_ids
model_inputs["input_ids"].append(input_ids)