hiyouga/LlamaFactory

Pattern Findings

1084 matches across 17 categories. Click a row to expand file-level details.

Unused Imports357 hits · 357 pts

Severity	File	Line
LOW	tests/data/test_mm_plugin.py	30
LOW	tests/data/test_mm_plugin.py	30
LOW	tests/data/test_mm_plugin.py	33
LOW	tests/data/test_mm_plugin.py	34
LOW	tests/data/test_template.py	28
LOW	docs/zh/conf.py	8
LOW	docs/en/conf.py	8
LOW	src/llamafactory/v1/config/__init__.py	15
LOW	src/llamafactory/v1/config/__init__.py	16
LOW	src/llamafactory/v1/config/__init__.py	16
LOW	src/llamafactory/v1/config/__init__.py	17
LOW	src/llamafactory/v1/config/__init__.py	17
LOW	src/llamafactory/v1/config/__init__.py	17
LOW	src/llamafactory/v1/config/__init__.py	18
LOW	src/llamafactory/v1/config/__init__.py	19
LOW	src/llamafactory/v1/config/__init__.py	20
LOW	src/llamafactory/v1/config/__init__.py	21
LOW	…afactory/v1/plugins/trainer_plugins/distributed/hub.py	15
LOW	…/llamafactory/v1/plugins/model_plugins/quantization.py	31
LOW	…/llamafactory/v1/plugins/model_plugins/quantization.py	31
LOW	…y/v1/plugins/model_plugins/kernels/liger_kernel_ops.py	27
LOW	…y/v1/plugins/model_plugins/kernels/liger_kernel_ops.py	53
LOW	…ins/model_plugins/kernels/ops/rms_norm/npu_rms_norm.py	30
LOW	…/v1/plugins/model_plugins/kernels/ops/rope/npu_rope.py	29
LOW	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	373
LOW	…v1/plugins/model_plugins/kernels/ops/mlp/npu_swiglu.py	29
LOW	src/llamafactory/v1/utils/packages.py	34
LOW	src/llamafactory/v1/utils/callbacks/__init__.py	15
LOW	src/llamafactory/v1/utils/callbacks/__init__.py	16
LOW	src/llamafactory/v1/utils/callbacks/__init__.py	16
LOW	src/llamafactory/v1/utils/callbacks/__init__.py	16
LOW	src/llamafactory/v1/utils/callbacks/logging_callback.py	15
LOW	src/llamafactory/v1/utils/callbacks/trainer_callback.py	15
LOW	src/llamafactory/v1/samplers/cli_sampler.py	88
LOW	src/llamafactory/chat/hf_engine.py	33
LOW	src/llamafactory/chat/hf_engine.py	33
LOW	src/llamafactory/chat/hf_engine.py	33
LOW	src/llamafactory/chat/hf_engine.py	34
LOW	src/llamafactory/chat/hf_engine.py	36
LOW	src/llamafactory/chat/hf_engine.py	37
LOW	src/llamafactory/chat/hf_engine.py	37
LOW	src/llamafactory/chat/hf_engine.py	37
LOW	src/llamafactory/chat/hf_engine.py	38
LOW	src/llamafactory/chat/hf_engine.py	38
LOW	src/llamafactory/chat/hf_engine.py	38
LOW	src/llamafactory/chat/hf_engine.py	38
LOW	src/llamafactory/chat/vllm_engine.py	34
LOW	src/llamafactory/chat/vllm_engine.py	39
LOW	src/llamafactory/chat/vllm_engine.py	39
LOW	src/llamafactory/chat/vllm_engine.py	39
LOW	src/llamafactory/chat/vllm_engine.py	40
LOW	src/llamafactory/chat/vllm_engine.py	40
LOW	src/llamafactory/chat/vllm_engine.py	40
LOW	src/llamafactory/chat/vllm_engine.py	40
LOW	src/llamafactory/chat/sglang_engine.py	29
LOW	src/llamafactory/chat/sglang_engine.py	29
LOW	src/llamafactory/chat/sglang_engine.py	29
LOW	src/llamafactory/chat/sglang_engine.py	29
LOW	src/llamafactory/chat/sglang_engine.py	40
LOW	src/llamafactory/chat/sglang_engine.py	40
297 more matches not shown…

Over-Commented Block289 hits · 289 pts

Severity	File	Line	Snippet
LOW	tests/conftest.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/check_license.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/test_freeze.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/test_pissa.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/test_full.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/test_base.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/test_lora.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/model_utils/test_misc.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/model_utils/test_visual.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/model_utils/test_add_tokens.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/model_utils/test_attention.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/model_utils/test_packing.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/model/model_utils/test_checkpointing.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/train/test_sft_trainer.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/eval/test_eval_template.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/e2e/test_train.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/e2e/test_sglang.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/e2e/test_chat.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/test_collator.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/test_loader.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/test_mm_plugin.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/test_formatter.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/test_converter.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/test_template.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/processor/test_feedback.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/processor/test_supervised.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/processor/test_pairwise.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/processor/test_unsupervised.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests/data/processor/test_processor_utils.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/conftest.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/core/test_data_engine.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/core/test_model_loader.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/core/utils/test_batching.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/core/utils/test_rendering.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/config/test_args_parser.py	1	# Copyright 2025 the LlamaFactory team.
LOW	…s_v1/plugins/trainer_plugins/distributed/test_fsdp2.py	1	# Copyright 2025 the LlamaFactory team.
LOW	…ainer_plugins/distributed/test_fsdp2_weight_convert.py	1	# Copyright 2025 the LlamaFactory team.
LOW	…s_v1/plugins/model_plugins/test_quantization_plugin.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/plugins/model_plugins/test_peft.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/plugins/model_plugins/test_kernel_plugin.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/plugins/model_plugins/test_init_plugin.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/plugins/model_plugins/test_ulysses_cp.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/plugins/data_plugins/test_converter.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/trainers/test_fsdp2_sft_trainer.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/accelerator/test_interface.py	1	# Copyright 2025 the LlamaFactory team.
LOW	tests_v1/sampler/test_cli_sampler.py	1	# Copyright 2025 the LlamaFactory team.
LOW	examples/train_full/qwen3vl_full_sft.yaml	41	ddp_timeout: 180000000
LOW	examples/train_full/qwen3_full_sft.yaml	41	# val_size: 0.1
LOW	examples/train_qlora/llama3_lora_sft_gptq.yaml	41	# per_device_eval_batch_size: 1
LOW	examples/train_qlora/llama3_lora_sft_awq.yaml	41	# per_device_eval_batch_size: 1
LOW	examples/train_qlora/llama3_lora_sft_aqlm.yaml	41	# per_device_eval_batch_size: 1
LOW	examples/train_qlora/qwen3_lora_sft_otfq.yaml	41	### eval
LOW	examples/train_qlora/qwen3_lora_sft_bnb_npu.yaml	41
LOW	examples/train_lora/qwen3_lora_dpo.yaml	41
LOW	examples/train_lora/qwen3_lora_sft_ds3.yaml	41	### eval
LOW	examples/train_lora/qwen3vl_lora_dpo.yaml	41	ddp_timeout: 180000000
LOW	examples/train_lora/qwen3_lora_pretrain.yaml	41	# val_size: 0.1
LOW	examples/train_lora/qwen3_lora_reward.yaml	41	# eval_dataset: dpo_en_demo
LOW	examples/train_lora/qwen3vl_lora_sft.yaml	41
LOW	examples/train_lora/qwen3_lora_kto.yaml	41	# per_device_eval_batch_size: 1
229 more matches not shown…

Hyper-Verbose Identifiers175 hits · 184 pts

Severity	File	Line	Snippet
LOW	tests/conftest.py	85	def _handle_device_visibility(items: list[Item]):
LOW	tests/conftest.py	109	def pytest_collection_modifyitems(config: Config, items: list[Item]):
LOW	tests/conftest.py	123	def _cleanup_distributed_state():
LOW	tests/conftest.py	166	def fix_valuehead_cpu_loading():
LOW	tests/conftest.py	172	def bypass_mistral_regex_check():
LOW	tests/model/test_freeze.py	46	def test_freeze_train_all_modules():
LOW	tests/model/test_freeze.py	57	def test_freeze_train_extra_modules():
LOW	tests/model/test_lora.py	58	def test_lora_train_qv_modules():
LOW	tests/model/test_lora.py	64	def test_lora_train_all_modules():
LOW	tests/model/test_lora.py	70	def test_lora_train_extra_modules():
LOW	tests/model/test_lora.py	76	def test_lora_train_old_adapters():
LOW	tests/model/test_lora.py	82	def test_lora_train_new_adapters():
LOW	tests/model/test_lora.py	91	def test_lora_train_valuehead():
LOW	tests/model/model_utils/test_visual.py	84	def test_visual_model_save_load():
LOW	tests/model/model_utils/test_packing.py	37	def test_get_seqlens_in_batch(attention_mask, golden_seq_lens):
LOW	tests/model/model_utils/test_checkpointing.py	43	def test_vanilla_checkpointing(disable_gradient_checkpointing: bool):
LOW	tests/model/model_utils/test_checkpointing.py	49	def test_unsloth_gradient_checkpointing():
LOW	tests/model/model_utils/test_checkpointing.py	62	def test_upcast_lmhead_output():
LOW	tests/data/test_collator.py	234	def _get_expected_position_ids(
LOW	tests/data/test_collator.py	274	def test_multimodal_collator_with_packing():
LOW	tests/data/test_mm_plugin.py	316	def test_llava_next_video_plugin():
LOW	tests/data/test_formatter.py	64	def test_multi_function_formatter():
LOW	tests/data/test_formatter.py	75	def test_default_tool_formatter():
LOW	tests/data/test_formatter.py	94	def test_default_tool_extractor():
LOW	tests/data/test_formatter.py	101	def test_default_multi_tool_extractor():
LOW	tests/data/test_formatter.py	193	def test_mistral_function_formatter():
LOW	tests/data/test_formatter.py	203	def test_mistral_multi_function_formatter():
LOW	tests/data/test_formatter.py	215	def test_mistral_tool_formatter():
LOW	tests/data/test_formatter.py	224	def test_mistral_tool_extractor():
LOW	tests/data/test_formatter.py	231	def test_mistral_multi_tool_extractor():
LOW	tests/data/test_formatter.py	244	def test_qwen_function_formatter():
LOW	tests/data/test_formatter.py	253	def test_qwen_multi_function_formatter():
LOW	tests/data/test_formatter.py	285	def test_qwen_multi_tool_extractor():
LOW	tests/data/test_template.py	133	def test_reasoning_encode_oneturn(cot_messages: bool, enable_thinking: bool):
LOW	tests/data/test_template.py	159	def test_reasoning_encode_multiturn(cot_messages: bool, enable_thinking: bool):
LOW	tests/data/test_template.py	188	def test_reasoning_encode_multiturn_discarding_history_cot(enable_thinking: bool, discarding_history_cot: bool):
LOW	tests/data/processor/test_supervised.py	48	def test_supervised_single_turn(num_samples: int):
LOW	tests/data/processor/test_supervised.py	77	def test_supervised_multi_turn(num_samples: int):
LOW	tests/data/processor/test_supervised.py	95	def test_supervised_train_on_prompt(num_samples: int):
LOW	tests/data/processor/test_supervised.py	113	def test_supervised_mask_history(num_samples: int):
LOW	tests/data/processor/test_pairwise.py	46	def _convert_sharegpt_to_openai(messages: list[dict[str, str]]) -> list[dict[str, str]]:
LOW	tests_v1/conftest.py	86	def _handle_device_visibility(items: list[Item]):
LOW	tests_v1/conftest.py	110	def pytest_collection_modifyitems(config: Config, items: list[Item]):
LOW	tests_v1/conftest.py	135	def _cleanup_distributed_state():
LOW	tests_v1/conftest.py	178	def bypass_mistral_regex_check():
LOW	tests_v1/core/test_model_loader.py	30	def test_tiny_qwen_with_kernel_plugin():
LOW	tests_v1/core/utils/test_batching.py	72	def test_batching_plugin_data_provider_batch_sizes():
LOW	tests_v1/core/utils/test_batching.py	121	def test_dynamic_batching_returns_none_when_token_budget_is_incomplete():
LOW	tests_v1/core/utils/test_batching.py	138	def test_dynamic_batching_fill_buffer_restarts_until_micro_batch_is_complete():
LOW	tests_v1/core/utils/test_batching.py	206	def test_dynamic_padding_free():
LOW	tests_v1/core/utils/test_batching.py	311	def test_dynamic_padding_free_returns_none_when_token_budget_is_incomplete():
LOW	tests_v1/core/utils/test_batching.py	323	def test_dynamic_padding_free_fill_buffer_restarts_until_micro_batch_is_complete():
LOW	tests_v1/core/utils/test_rendering.py	118	def test_chatml_rendering_remote(num_samples: int):
LOW	…s_v1/plugins/trainer_plugins/distributed/test_fsdp2.py	33	def collect_non_persistent_buffers(model):
LOW	…s_v1/plugins/model_plugins/test_quantization_plugin.py	24	def check_quantization_status(model):
LOW	tests_v1/plugins/model_plugins/test_peft.py	60	def test_find_all_linear_modules(model):
LOW	tests_v1/plugins/model_plugins/test_peft.py	76	def test_get_freeze_model_layers(model):
LOW	tests_v1/plugins/model_plugins/test_peft.py	94	def test_get_freeze_model_modules(model):
LOW	tests_v1/plugins/model_plugins/test_peft.py	109	def test_load_adapter_single_for_inference(model, adapter_path):
LOW	tests_v1/plugins/model_plugins/test_peft.py	116	def test_load_adapter_resume_train(model, adapter_path):
115 more matches not shown…

Slop Phrases54 hits · 92 pts

Severity	File	Line	Snippet
MEDIUM	data/kto_en_demo.json	67	"content": "Certainly, measuring the results of a marketing strategy and making adjustments based on those metri
MEDIUM	data/kto_en_demo.json	394	"content": "Using Unreal's Gameplay Ability System (GAS) in conjunction with interpolation and prediction can pr
LOW	data/kto_en_demo.json	903	"content": "I apologize for the confusion. The `unique_id` parameter in the `momepy.Tessellation` function expec
MEDIUM	data/kto_en_demo.json	2012	"content": "Two-factor authentication (2FA) adds an extra layer of security by requiring users to provide two fo
MEDIUM	data/kto_en_demo.json	2114	"content": "To adapt the program to handle in-place modification or the creation of new objects based on a boole
MEDIUM	data/kto_en_demo.json	2449	"content": "I'm not sure where you've heard that information, but as an AI language model, I can share some fact
MEDIUM	data/kto_en_demo.json	2790	"content": "To derive the original matrix from the rotated one, you would need to perform a 90 degrees counter-c
MEDIUM	data/kto_en_demo.json	3013	"content": "The genetic factors that contribute to the intricate design of the peacock's tail feathers are quite
MEDIUM	data/kto_en_demo.json	3585	"content": "As an AI language model,I cannot determine the sentiment of the product review without further conte
MEDIUM	data/kto_en_demo.json	3611	"content": "I'm unable to provide you with a real-time percentage of population living in poverty in Marlborough
LOW	data/kto_en_demo.json	3690	"content": "Firstly, as a fitness trainer, I highly recommend consulting with a healthcare professional before e
MEDIUM	data/kto_en_demo.json	3850	"content": "Since each medium-sized box measures 2 feet on all sides, its volume will be: 222 = 8 cubic feet.
MEDIUM	data/kto_en_demo.json	4774	"content": "In Feng Shui, the five elements—wood, fire, earth, metal, and water—are believed to interact in cert
MEDIUM	data/kto_en_demo.json	4897	"content": "Sure, I understand the problem. However, I'm a large language model, I cannot provide a correct answ
MEDIUM	data/kto_en_demo.json	4923	"content": "As an AI language model, I am not able to provide program codes or algorithms. However, I can provid
MEDIUM	data/alpaca_en_demo.json	405	"output": "I am sorry, but as an AI language model, I do not have the data or access to real-time information to det
MEDIUM	data/alpaca_en_demo.json	930	"output": "I'm sorry, but I don't have access to external articles or news sources so I'm unable to read or summariz
LOW	data/alpaca_en_demo.json	1175	"output": "Here is an example of HTML code that can be used to create a web page that displays the temperature of th
MEDIUM	data/alpaca_en_demo.json	3330	"output": "As an AI, I don't have a physical house, so I cannot provide a description of it. Can I help you with som
MEDIUM	data/alpaca_en_demo.json	3900	"output": "Thank you for considering my request. Please let me know if you need any additional information, and I lo
MEDIUM	data/alpaca_en_demo.json	3905	"output": "I'm sorry, but I'm unable to come into work today due to unforeseen medical issues. I woke up with a seve
MEDIUM	data/alpaca_en_demo.json	3975	"output": "As an AI, I don’t have access to real-time information such as pricing, and due to the fact that movie ti
MEDIUM	data/alpaca_en_demo.json	4090	"output": "I am sorry, but as an AI language model, I do not have access to up-to-date information on housing prices
MEDIUM	data/alpaca_en_demo.json	4505	"output": "Sure, here is a simple example of a class for a car:\n\n```python\n\nclass Car:\n \n def __init__(sel
MEDIUM	data/alpaca_en_demo.json	4715	"output": "I'm sorry, but as an AI language model, I'm unable to create or display graphical content. However, I can
MEDIUM	data/alpaca_en_demo.json	4715	"output": "I'm sorry, but as an AI language model, I'm unable to create or display graphical content. However, I can
MEDIUM	data/alpaca_en_demo.json	4870	"output": "As an AI, I can assist you in coming up with design ideas and concepts for the logo. However, I'm unable
MEDIUM	data/alpaca_zh_demo.json	4470	"output": "As an AI language model I am capable of analyzing text and identifying emotions, however, the sentence pr
MEDIUM	data/glaive_toolcall_en_demo.json	1232	"value": "I'm sorry, but I'm unable to perform external tasks like ordering a pizza. My capabilities are current
MEDIUM	data/glaive_toolcall_en_demo.json	1295	"value": "Analyzing the motivations of a protagonist in a narrative can be a complex task that requires a deep u
MEDIUM	data/glaive_toolcall_en_demo.json	3349	"value": "To create a stacked bar chart in D3.js, you can modify the code to use the D3.js `stack()` function to
MEDIUM	data/glaive_toolcall_en_demo.json	3452	"value": "I'm sorry, but I'm unable to assist with booking flights as it's an external task. My current capabili
MEDIUM	data/glaive_toolcall_en_demo.json	4143	"value": "I'm sorry, but I'm unable to assist with that. My current capabilities allow me to calculate Body Mass
MEDIUM	data/glaive_toolcall_en_demo.json	4328	"value": "I'm sorry, but I'm unable to assist with that. My current capabilities are limited to generating invoi
MEDIUM	data/glaive_toolcall_en_demo.json	5069	"value": "I'm sorry, but I'm unable to assist with booking flights. My current capabilities are limited to calcu
MEDIUM	data/glaive_toolcall_en_demo.json	5818	"value": "I'm sorry, but I'm unable to perform external tasks like ordering a pizza. My current capabilities are
MEDIUM	data/glaive_toolcall_en_demo.json	6538	"value": "I'm sorry, but I'm unable to perform external tasks such as ordering a pizza. My current capabilities
MEDIUM	data/glaive_toolcall_en_demo.json	6667	"value": "I'm sorry, but I'm unable to assist with that. My current capabilities are limited to calculating the
MEDIUM	data/glaive_toolcall_en_demo.json	6725	"value": "I'm sorry, but I'm unable to assist with that. Booking a flight is an external task and I don't have a
MEDIUM	data/glaive_toolcall_en_demo.json	6809	"value": "I'm sorry, but I'm unable to perform external tasks like ordering a pizza. My capabilities are limited
MEDIUM	data/glaive_toolcall_en_demo.json	6901	"value": "Sure, here is how you can compile the recipe from the JSON data:\nRecipe: Tomato Spaghetti\nIngredient
MEDIUM	data/glaive_toolcall_en_demo.json	7020	"value": "I'm sorry, but I'm unable to assist with that. My current capabilities are limited to the functions pr
MEDIUM	data/glaive_toolcall_en_demo.json	7592	"value": "I'm sorry, but I'm unable to assist with booking flights. My current capabilities are limited to gener
MEDIUM	data/glaive_toolcall_en_demo.json	8510	"value": "I'm sorry, but I'm unable to assist with that. Booking a flight is an external task and I don't have a
MEDIUM	data/glaive_toolcall_en_demo.json	8557	"value": "I'm sorry, but I'm unable to book movie tickets as it's an external task and I don't have a function p
MEDIUM	data/glaive_toolcall_en_demo.json	8823	"value": "I'm sorry, but I'm unable to assist with booking flights. My current capabilities are limited to calcu
MEDIUM	data/glaive_toolcall_en_demo.json	8984	"value": "I'm sorry, but I'm unable to assist with that. My current capabilities are limited to the functions pr
LOW	data/glaive_toolcall_en_demo.json	1198	"value": "Here is your new password: a9B7$#fG3&Z1. Please make sure to save it in a secure place."
LOW	data/glaive_toolcall_en_demo.json	1538	"value": "Here is your new password: aB3#fG7!kL9@. Please make sure to save it in a secure place."
LOW	data/glaive_toolcall_en_demo.json	3130	"value": "Here is your new password: aB3#fG7!kL9@. Please make sure to save it in a secure place."
LOW	data/glaive_toolcall_en_demo.json	3307	"value": "Here is your new password: aB3#fG7!kL9@. Please make sure to save it in a secure place."
LOW	data/glaive_toolcall_en_demo.json	5718	"value": "Here is your new password: aB3#fG7!kL9@. Please make sure to save it in a secure place."
LOW	data/glaive_toolcall_en_demo.json	6775	"value": "Here is your new password: aB3#fG7!kL9@. Please make sure to save it in a secure place."
LOW	src/llamafactory/chat/sglang_engine.py	127	self._cleanup_server() # make sure to clean up any started process

Deep Nesting83 hits · 82 pts

Severity	File	Line
LOW	tests/data/test_collator.py	140
LOW	tests/data/test_mm_plugin.py	117
LOW	scripts/vllm_infer.py	47
LOW	scripts/llama_pro.py	40
LOW	scripts/convert_ckpt/llamafy_qwen.py	39
LOW	scripts/stat_utils/cal_mfu.py	86
LOW	src/llamafactory/launcher.py	38
LOW	src/llamafactory/v1/launcher.py	34
LOW	src/llamafactory/v1/core/base_trainer.py	235
LOW	src/llamafactory/v1/core/utils/rendering.py	136
LOW	src/llamafactory/v1/config/arg_utils.py	61
LOW	src/llamafactory/v1/plugins/trainer_plugins/batching.py	118
LOW	…actory/v1/plugins/trainer_plugins/distributed/fsdp2.py	76
LOW	…actory/v1/plugins/trainer_plugins/distributed/fsdp2.py	193
LOW	…actory/v1/plugins/trainer_plugins/distributed/fsdp2.py	437
LOW	src/llamafactory/v1/plugins/model_plugins/peft.py	191
LOW	…/v1/plugins/model_plugins/kernels/ops/rope/npu_rope.py	136
LOW	…ry/v1/plugins/model_plugins/templates/qwen3_nothink.py	61
LOW	…ry/v1/plugins/model_plugins/templates/qwen3_nothink.py	170
LOW	…amafactory/v1/plugins/model_plugins/templates/qwen3.py	86
LOW	…amafactory/v1/plugins/model_plugins/templates/qwen3.py	111
LOW	…amafactory/v1/plugins/model_plugins/templates/qwen3.py	220
LOW	…ins/model_plugins/parallelization/sequence_parallel.py	129
LOW	src/llamafactory/v1/plugins/data_plugins/converter.py	104
LOW	src/llamafactory/chat/hf_engine.py	73
LOW	src/llamafactory/chat/chat_model.py	47
LOW	src/llamafactory/hparams/parser.py	304
LOW	src/llamafactory/model/adapter.py	141
LOW	src/llamafactory/model/loader.py	131
LOW	src/llamafactory/model/model_utils/attention.py	31
LOW	src/llamafactory/model/model_utils/quantization.py	82
LOW	src/llamafactory/model/model_utils/liger_kernel.py	30
LOW	src/llamafactory/model/model_utils/moe.py	160
LOW	src/llamafactory/train/trainer_utils.py	151
LOW	src/llamafactory/train/trainer_utils.py	200
LOW	src/llamafactory/train/trainer_utils.py	288
LOW	src/llamafactory/train/trainer_utils.py	372
LOW	src/llamafactory/train/tuner.py	68
LOW	src/llamafactory/train/dpo/trainer.py	45
LOW	src/llamafactory/train/pt/workflow.py	36
LOW	src/llamafactory/train/sft/trainer.py	50
LOW	src/llamafactory/train/ppo/trainer.py	311
LOW	src/llamafactory/train/kto/trainer.py	44
LOW	src/llamafactory/train/rm/trainer.py	113
LOW	src/llamafactory/api/chat.py	73
LOW	src/llamafactory/webui/chatter.py	101
LOW	src/llamafactory/webui/control.py	160
LOW	src/llamafactory/webui/control.py	209
LOW	src/llamafactory/webui/components/export.py	47
LOW	src/llamafactory/webui/components/chatbot.py	34
LOW	src/llamafactory/webui/components/chatbot.py	49
LOW	src/llamafactory/data/formatter.py	72
LOW	src/llamafactory/data/mm_plugin.py	257
LOW	src/llamafactory/data/mm_plugin.py	278
LOW	src/llamafactory/data/mm_plugin.py	624
LOW	src/llamafactory/data/mm_plugin.py	1015
LOW	src/llamafactory/data/mm_plugin.py	1118
LOW	src/llamafactory/data/mm_plugin.py	1158
LOW	src/llamafactory/data/mm_plugin.py	1930
LOW	src/llamafactory/data/mm_plugin.py	2358
23 more matches not shown…

Decorative Section Separators20 hits · 63 pts

Severity	File	Line	Snippet
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	45	# ---------------------------------------------------------------------------
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	47	# ---------------------------------------------------------------------------
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	245	# ---------------------------------------------------------------------------
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	247	# ---------------------------------------------------------------------------
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	267	# ---------------------------------------------------------------------------
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	269	# ---------------------------------------------------------------------------
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	328	# ---------------------------------------------------------------------------
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	330	# ---------------------------------------------------------------------------
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	349	# ---------------------------------------------------------------------------
MEDIUM	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	351	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	32	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	34	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	50	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	53	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	181	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	184	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	285	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	287	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	352	# ---------------------------------------------------------------------------
MEDIUM	…s/model_plugins/kernels/ops/mlp/triton_grouped_gemm.py	354	# ---------------------------------------------------------------------------

Cross-File Repetition10 hits · 50 pts

Severity	File	Snippet
HIGH	src/llamafactory/v1/core/base_sampler.py	batch infer samples. args: dataset: torch dataset. returns: list of samples.
HIGH	src/llamafactory/v1/core/utils/inference_engine.py	batch infer samples. args: dataset: torch dataset. returns: list of samples.
HIGH	src/llamafactory/v1/core/utils/inference_engine.py	batch infer samples. args: dataset: torch dataset. returns: list of samples.
HIGH	src/llamafactory/data/template.py	[tool_results] {"content": {{content}}}[/tool_results]
HIGH	src/llamafactory/data/template.py	[tool_results] {"content": {{content}}}[/tool_results]
HIGH	src/llamafactory/data/template.py	[tool_results] {"content": {{content}}}[/tool_results]
HIGH	src/llamafactory/data/template.py	[tool_results]{"content": {{content}}}[/tool_results]
HIGH	src/llamafactory/data/template.py	[tool_results]{"content": {{content}}}[/tool_results]
HIGH	src/llamafactory/data/template.py	[tool_results]{"content": {{content}}}[/tool_results]
HIGH	src/llamafactory/data/template.py	[tool_results]{"content": {{content}}}[/tool_results]

Excessive Try-Catch Wrapping48 hits · 48 pts

Severity	File	Line	Snippet
LOW	scripts/qwen_omni_merge.py	86	except Exception:
LOW	scripts/qwen_omni_merge.py	135	except Exception:
LOW	scripts/convert_ckpt/llamafy_qwen.py	32	except Exception:
LOW	scripts/convert_ckpt/llamafy_qwen.py	157	except Exception as e:
LOW	scripts/convert_ckpt/llamafy_baichuan2.py	104	except Exception as e:
LOW	…actory/v1/plugins/trainer_plugins/distributed/fsdp2.py	408	except Exception as e:
LOW	src/llamafactory/v1/plugins/model_plugins/rendering.py	36	except Exception as exc:
LOW	src/llamafactory/v1/plugins/model_plugins/peft.py	334	except Exception as e:
LOW	…afactory/v1/plugins/model_plugins/kernels/interface.py	71	except Exception as e:
LOW	…/v1/plugins/model_plugins/kernels/ops/rope/npu_rope.py	184	except Exception as e:
LOW	src/llamafactory/v1/utils/packages.py	44	except Exception:
LOW	src/llamafactory/v1/samplers/cli_sampler.py	101	except Exception:
LOW	src/llamafactory/chat/sglang_engine.py	122	except Exception as e:
LOW	src/llamafactory/chat/sglang_engine.py	125	except Exception as e:
LOW	src/llamafactory/chat/sglang_engine.py	137	except Exception as e:
LOW	src/llamafactory/chat/sglang_engine.py	288	except Exception:
LOW	src/llamafactory/chat/chat_model.py	180	except Exception:
LOW	src/llamafactory/hparams/model_args.py	250	except Exception as e:
LOW	src/llamafactory/model/loader.py	92	except Exception as e:
LOW	src/llamafactory/model/loader.py	109	except Exception as e:
LOW	src/llamafactory/model/patcher.py	426	except Exception:
LOW	src/llamafactory/model/model_utils/valuehead.py	47	except Exception as err:
LOW	src/llamafactory/model/model_utils/valuehead.py	53	except Exception as err:
LOW	src/llamafactory/train/fp8_utils.py	103	except Exception as e:
LOW	src/llamafactory/train/trainer_utils.py	876	except Exception:
LOW	src/llamafactory/train/callbacks.py	394	except Exception:
LOW	src/llamafactory/train/tuner.py	135	except Exception as e:
LOW	src/llamafactory/train/tuner.py	250	except Exception as e:
LOW	src/llamafactory/train/ppo/trainer.py	279	except Exception:
LOW	src/llamafactory/train/mca/workflow.py	156	except Exception:
LOW	src/llamafactory/train/mca/workflow.py	158	except Exception as exc:
LOW	src/llamafactory/api/common.py	66	except Exception:
LOW	src/llamafactory/api/common.py	95	except Exception as e:
LOW	src/llamafactory/webui/common.py	55	except Exception:
LOW	src/llamafactory/webui/common.py	79	except Exception:
LOW	src/llamafactory/webui/common.py	149	except Exception as err:
LOW	src/llamafactory/webui/common.py	159	except Exception:
LOW	src/llamafactory/webui/components/chatbot.py	45	except Exception:
LOW	src/llamafactory/webui/components/data.py	47	except Exception:
LOW	src/llamafactory/data/parser.py	111	except Exception as err:
LOW	src/llamafactory/data/data_utils.py	194	except Exception:
LOW	src/llamafactory/extras/misc.py	44	except Exception:
LOW	src/llamafactory/extras/env.py	64	except Exception:
LOW	src/llamafactory/extras/env.py	71	except Exception:
LOW	src/llamafactory/extras/env.py	78	except Exception:
LOW	src/llamafactory/extras/env.py	85	except Exception:
LOW	src/llamafactory/extras/env.py	94	except Exception:
LOW	src/llamafactory/extras/packages.py	38	except Exception:

Docstring Block Structure7 hits · 35 pts

Severity	File	Line	Snippet
HIGH	…mafactory/v1/plugins/model_plugins/kernels/registry.py	40	Decorator to register a kernel class. The class must inherit from :class:`BaseKernel` and specify ``_kernel_id`
HIGH	…y/v1/plugins/model_plugins/kernels/liger_kernel_ops.py	64	Applies the Liger kernel to the model. Args: **kwargs: Must include ``model``. Optional ``use_kerne
HIGH	…/llamafactory/v1/plugins/model_plugins/kernels/base.py	68	Applies the kernel optimization to the model. Args: **kwargs: Arbitrary keyword arguments, usually
HIGH	…ins/model_plugins/kernels/ops/rms_norm/npu_rms_norm.py	135	Iterate the model and apply NPU-optimized forward to matched RMSNorm modules. Matches modules whose class name
HIGH	…/v1/plugins/model_plugins/kernels/ops/rope/npu_rope.py	137	Apply RoPE acceleration by monkey-patching ``apply_rotary_pos_emb``. Iterates through the model's modules to fi
HIGH	…v1/plugins/model_plugins/kernels/ops/mlp/npu_swiglu.py	129	Applies the NPU fused SwiGLU kernel to the model. Args: **kwargs: Keyword arguments containing the
HIGH	…plugins/model_plugins/kernels/ops/mlp/npu_fused_moe.py	308	Applies the NPU fused MoE kernel to the model. Args: **kwargs: Keyword arguments containing the mod

Self-Referential Comments15 hits · 34 pts

Severity	File	Line	Snippet
MEDIUM	tests_v1/plugins/model_plugins/test_peft.py	43	# Create a dummy adapter
MEDIUM	data/kto_en_demo.json	887	"content": "To smoothen the output polygons without creating gaps or overlaps, you can use a combination of libr
MEDIUM	data/kto_en_demo.json	895	"content": "I apologize for the confusion. Let's try a different approach using the `TopologicalPreserveSimplifi
MEDIUM	data/kto_en_demo.json	907	"content": "I have the following code:\n#%% Generate geoTiffs with index values based on one large geotiff with
MEDIUM	data/kto_en_demo.json	919	"content": "To smoothen the output polygons without creating gaps or overlays between the polygons, you can use
MEDIUM	data/alpaca_en_demo.json	2655	"output": "In order to build a random forest regression model to predict house prices, we need to organize the data
MEDIUM	data/alpaca_en_demo.json	4405	"output": "The most efficient way to implement a sparse matrix in Python depends on the specifics of the matrix and
MEDIUM	data/glaive_toolcall_zh_demo.json	7807	"value": "Sure, here's a sample Python code to generate the Excel table and some SQL queries to filter the anima
MEDIUM	data/glaive_toolcall_en_demo.json	567	"value": "Yes, I can help you with that. Here's a sample code snippet that should do what you're looking for:\n`
MEDIUM	data/glaive_toolcall_en_demo.json	575	"value": "Yes, you can modify the code snippet to rank the cities in ascending order by changing the `reverse` p
MEDIUM	data/glaive_toolcall_en_demo.json	1625	"value": "To examine real-time usage patterns of public electric vehicle charging stations in a specific city us
MEDIUM	data/glaive_toolcall_en_demo.json	2422	"value": "There are several algorithms that can be used to solve a Rubik's cube puzzle in Ruby programming langu
MEDIUM	data/glaive_toolcall_en_demo.json	5185	"value": "Sure, here's a Python code that can generate a sequence of clues that reveal the identity of the grand
MEDIUM	src/llamafactory/data/collator.py	123	# Create a non-padding mask.
MEDIUM	src/llamafactory/data/collator.py	128	# Create a lower triangular mask.

Magic Placeholder Names3 hits · 15 pts

Severity	File	Line	Snippet
HIGH	README.md	821	1. Add `swanlab_api_key=<your_api_key>` to the yaml file, and set it to your [API key](https://swanlab.cn/settings).
HIGH	README_zh.md	825	方式一：在 yaml 文件中添加 `swanlab_api_key=<your_api_key>` ，并设置为你的 [API 密钥](https://swanlab.cn/settings)。
HIGH	data/dpo_zh_demo.json	3735	"value": "创建一个完整的程序像这样将是一个复杂且漫长的过程，涉及图形和音频处理。然而，我可以指导您完成初始步骤，并为您提供资源，帮助您构建项目的简单文本版本。\n\n要获取天气数据，您可以使用OpenWeatherMa

Verbosity Indicators7 hits · 12 pts

Severity	File	Line	Snippet
LOW	data/glaive_toolcall_zh_demo.json	7017	"value": "计算抛掷三颗骰子得到9点或以上的概率，其中至少有一颗骰子是质数，我们可以使用包含与排除原则。\n首先，我们需要计算在没有限制的情况下抛掷三颗骰子得到9点或以上的概率。这可以通过计算得到9点或以上的方式数，
LOW	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	167	# Step 1: Scatter grad_output to expert buffer
LOW	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	170	# Step 2: FC2 backward
LOW	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	191	# Step 3: Routing weight backward
LOW	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	200	# Step 4: SiLU gate backward
LOW	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	210	# Step 5: FC1 backward
LOW	…lugins/model_plugins/kernels/ops/mlp/cuda_fused_moe.py	231	# Step 6: Gather gradients back to original positions

Redundant / Tautological Comments7 hits · 8 pts

Severity	File	Line	Snippet
LOW	data/alpaca_en_demo.json	4535	"output": "Here is a function in Python that takes in a year as an input parameter and returns whether it is a leap
LOW	data/glaive_toolcall_zh_demo.json	4859	"value": "```python\ndef calculate_summary(array, divisor):\n # Sort the array in descending order\n array
LOW	data/glaive_toolcall_zh_demo.json	4859	"value": "```python\ndef calculate_summary(array, divisor):\n # Sort the array in descending order\n array
LOW	data/alpaca_zh_demo.json	275	"output": "def calculate_sum(numbers):\n if not isinstance(numbers, list): # Check if input is a list\n r
LOW	src/llamafactory/v1/core/base_trainer.py	326	# Check if max_steps is reached
LOW	src/llamafactory/train/ppo/trainer.py	86	# Check if TRL version is compatible (0.8.6 <= version <= 0.9.6)
LOW	src/llamafactory/data/collator.py	310	# Check if position_ids shape matches expected shape.

Fake / Example Data4 hits · 6 pts

Severity	File	Line	Snippet
LOW	data/glaive_toolcall_zh_demo.json	664	"value": "在LaTeX中，你可以通过使用`endfloat`包来实现这一点。以下是方法：\n1. 在你的LaTeX文档的预览部分添加`usepackage{endfloat}`。\n2. 在你希望图表出现在文档中的
LOW	data/glaive_toolcall_zh_demo.json	664	"value": "在LaTeX中，你可以通过使用`endfloat`包来实现这一点。以下是方法：\n1. 在你的LaTeX文档的预览部分添加`usepackage{endfloat}`。\n2. 在你希望图表出现在文档中的
LOW	data/glaive_toolcall_zh_demo.json	672	"value": "在您的LaTeX文档中，您可以通过使用`tableofcontents`命令来创建目录。以下是方法：\n1. 在您希望目录出现在文档中的位置添加`tableofcontents`命令。\n2. 编译您的L
LOW	data/glaive_toolcall_zh_demo.json	672	"value": "在您的LaTeX文档中，您可以通过使用`tableofcontents`命令来创建目录。以下是方法：\n1. 在您希望目录出现在文档中的位置添加`tableofcontents`命令。\n2. 编译您的L

Synthetic Comment Markers2 hits · 5 pts

Severity	File	Line	Snippet
HIGH	tests/data/test_template.py	236	"# ollama modelfile auto-generated by llamafactory\n\n"
HIGH	src/llamafactory/data/template.py	323	modelfile = "# ollama modelfile auto-generated by llamafactory\n\n"

AI Slop Vocabulary2 hits · 4 pts

Severity	File	Line	Snippet
MEDIUM	data/kto_en_demo.json	2769	"content": "As an Azure Cloud Engineer working with Microsoft Azure, you can indeed utilize Azure Active Directo
MEDIUM	data/alpaca_en_demo.json	3485	"output": "John Smith's Resume\n\nSummary:\n\nAn experienced and highly skilled software engineer with over 5 years

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet
LOW	examples/ascend/qwen3_5_full_sft_fsdp2.yaml	2	# Usage:

Score History

Severity Breakdown

Pattern Findings