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

Jump to bottom

fix for qwen w lora #906

Merged
merged 1 commit into from
Nov 30, 2023
Merged

fix for qwen w lora #906

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
13 changes: 10 additions & 3 deletions src/axolotl/utils/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,15 +412,22 @@ def load_model(
module.to(torch.float32)

needs_fa2_dtype = cfg.adapter or cfg.fsdp
skip_prepare_model_for_kbit_training = False

if cfg.model_config_type == "qwen" and cfg.adapter == "lora":
# Qwen doesn't play nicely with LoRA if this is enabled
skip_prepare_model_for_kbit_training = True

if (cfg.adapter == "lora" and load_in_8bit) or (
cfg.adapter == "qlora" and cfg.load_in_4bit
):
LOG.info("converting PEFT model w/ prepare_model_for_kbit_training")
if cfg.gradient_checkpointing:
model.gradient_checkpointing_enable()
model = prepare_model_for_kbit_training(
model, use_gradient_checkpointing=cfg.gradient_checkpointing
)
if not skip_prepare_model_for_kbit_training:
model = prepare_model_for_kbit_training(
model, use_gradient_checkpointing=cfg.gradient_checkpointing
)
needs_fa2_dtype = True

# LlamaRMSNorm layers are in fp32 after kbit_training or full finetune, so we need to
Expand Down