423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-15 19:30:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix baichuan templates

Browse Source
This commit is contained in:
hiyouga
2023-09-07 18:54:14 +08:00
parent 0531886e1f
commit 85b1f6632a
9 changed files with 53 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/llmtuner/tuner/core/loader.py
View File

@@ -15,9 +15,13 @@ from transformers import (
)
from transformers.utils import check_min_version
from transformers.utils.versions import require_version
from transformers.deepspeed import is_deepspeed_zero3_enabled
from trl import AutoModelForCausalLMWithValueHead
try:
from transformers.deepspeed import is_deepspeed_zero3_enabled
except ImportError:
from transformers.integrations import is_deepspeed_zero3_enabled
from llmtuner.extras.logging import reset_logging, get_logger
from llmtuner.extras.misc import count_parameters, prepare_model_for_training
from llmtuner.extras.save_and_load import load_valuehead_params
@@ -91,7 +95,7 @@ def load_model_and_tokenizer(
setattr(config, "use_logn_attn", True)
logger.info("Using dynamic NTK scaling.")
elif hasattr(config, "rope_scaling"): # for LLaMA models
elif hasattr(config, "rope_scaling"): # for LLaMA and Falcon models
require_version("transformers>=4.31.0", "RoPE scaling requires transformers>=4.31.0")
if is_trainable: