add license

Former-commit-id: d87108daa6

scripts/cal_flops.py

@@ -1,7 +1,20 @@
 # coding=utf-8
-# Calculates the flops of pre-trained models.
-# Usage: python cal_flops.py --model_name_or_path path_to_model --batch_size 1 --seq_length 512
-# Inspired by: https://www.deepspeed.ai/tutorials/flops-profiler/
+# Copyright 2024 Microsoft Corporation and the LlamaFactory team.
+#
+# This code is inspired by Microsoft's DeepSpeed library.
+# https://www.deepspeed.ai/tutorials/flops-profiler/
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
 import fire
 import torch
@@ -17,6 +30,10 @@ def calculate_flops(
     seq_length: int = 256,
     flash_attn: str = "auto",
 ):
+    r"""
+    Calculates the flops of pre-trained models.
+    Usage: python cal_flops.py --model_name_or_path path_to_model --batch_size 1 --seq_length 512
+    """
     with get_accelerator().device(0):
         chat_model = ChatModel(dict(model_name_or_path=model_name_or_path, template="empty", flash_attn=flash_attn))
         fake_input = torch.ones((batch_size, seq_length), dtype=torch.long, device=chat_model.model.device)

scripts/cal_lr.py

@@ -1,7 +1,20 @@
 # coding=utf-8
-# Calculates the optimal learning rate for 7B/13B models using LLaMA's hyper-parameters.
-# Usage: python cal_lr.py --model_name_or_path path_to_model --dataset alpaca_en --cutoff_len 1024 --batch_size 16
-# Inspired by: https://github.com/imoneoi/openchat/blob/master/ochat/training_deepspeed/train.py
+# Copyright 2024 imoneoi and the LlamaFactory team.
+#
+# This code is inspired by imoneoi's OpenChat library.
+# https://github.com/imoneoi/openchat/blob/3.6.0/ochat/training_deepspeed/train.py
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
 import math
 from typing import Literal
@@ -32,6 +45,10 @@ def calculate_lr(
     cutoff_len: int = 1024,  # i.e. maximum input length during training
     is_mistral: bool = False,  # mistral model uses a smaller learning rate,
 ):
+    r"""
+    Calculates the optimal learning rate for 7B/13B models using LLaMA's hyper-parameters.
+    Usage: python cal_lr.py --model_name_or_path path_to_model --dataset alpaca_en --cutoff_len 1024 --batch_size 16
+    """
     model_args, data_args, training_args, _, _ = get_train_args(
         dict(
             stage=stage,

scripts/cal_ppl.py

@@ -1,6 +1,17 @@
 # coding=utf-8
-# Calculates the ppl on the dataset of the pre-trained models.
-# Usage: python cal_ppl.py --model_name_or_path path_to_model --save_name ppl.json
+# Copyright 2024 the LlamaFactory team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
 import json
 from dataclasses import dataclass
@@ -56,6 +67,10 @@ def cal_ppl(
     max_samples: Optional[int] = None,
     train_on_prompt: bool = False,
 ):
+    r"""
+    Calculates the ppl on the dataset of the pre-trained models.
+    Usage: python cal_ppl.py --model_name_or_path path_to_model --save_name ppl.json
+    """
     model_args, data_args, training_args, finetuning_args, _ = get_train_args(
         dict(
             stage=stage,

scripts/length_cdf.py

@@ -1,6 +1,17 @@
 # coding=utf-8
-# Calculates the distribution of the input lengths in the dataset.
-# Usage: python length_cdf.py --model_name_or_path path_to_model --dataset alpaca_en --template default
+# Copyright 2024 the LlamaFactory team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
 from collections import defaultdict
 
@@ -19,6 +30,10 @@ def length_cdf(
     template: str = "default",
     interval: int = 1000,
 ):
+    r"""
+    Calculates the distribution of the input lengths in the dataset.
+    Usage: python length_cdf.py --model_name_or_path path_to_model --dataset alpaca_en --template default
+    """
     model_args, data_args, training_args, _, _ = get_train_args(
         dict(
             stage="sft",

scripts/llama_pro.py

@@ -1,7 +1,20 @@
 # coding=utf-8
-# Performs block expansion for LLaMA, Mistral, Qwen1.5 or Yi models.
-# Usage: python llama_pro.py --model_name_or_path meta-llama/Llama-2-7b-hf --output_dir llama2_pro --num_expand 8
-# Inspired by: https://github.com/TencentARC/LLaMA-Pro/blob/main/scripts/block_expansion.py
+# Copyright 2024 Tencent Inc. and the LlamaFactory team.
+#
+# This code is inspired by Tencent's LLaMA-Pro library.
+# https://github.com/TencentARC/LLaMA-Pro/blob/main/scripts/block_expansion.py
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
 import json
 import os
@@ -37,6 +50,10 @@ def block_expansion(
     shard_size: Optional[str] = "2GB",
     save_safetensors: Optional[bool] = False,
 ):
+    r"""
+    Performs block expansion for LLaMA, Mistral, Qwen1.5 or Yi models.
+    Usage: python llama_pro.py --model_name_or_path meta-llama/Llama-2-7b-hf --output_dir llama2_pro --num_expand 8
+    """
     config: "PretrainedConfig" = AutoConfig.from_pretrained(model_name_or_path)
     num_layers = getattr(config, "num_hidden_layers")
     setattr(config, "num_hidden_layers", num_layers + num_expand)

scripts/llamafy_baichuan2.py

@@ -1,8 +1,17 @@
 # coding=utf-8
-# Converts the Baichuan2-7B model in the same format as LLaMA2-7B.
-# Usage: python llamafy_baichuan2.py --input_dir input --output_dir output
-# Inspired by: https://huggingface.co/fireballoon/baichuan-llama-7b/blob/main/convert_baichuan_to_llama.py
-# Converted model: https://huggingface.co/hiyouga/Baichuan2-7B-Base-LLaMAfied
+# Copyright 2024 the LlamaFactory team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
 import json
 import os
@@ -79,6 +88,11 @@ def save_config(input_dir: str, output_dir: str):
 def llamafy_baichuan2(
     input_dir: str, output_dir: str, shard_size: Optional[str] = "2GB", save_safetensors: Optional[bool] = False
 ):
+    r"""
+    Converts the Baichuan2-7B model in the same format as LLaMA2-7B.
+    Usage: python llamafy_baichuan2.py --input_dir input --output_dir output
+    Converted model: https://huggingface.co/hiyouga/Baichuan2-7B-Base-LLaMAfied
+    """
     try:
         os.makedirs(output_dir, exist_ok=False)
     except Exception as e:

scripts/llamafy_qwen.py

@@ -1,7 +1,17 @@
 # coding=utf-8
-# Converts the Qwen models in the same format as LLaMA2.
-# Usage: python llamafy_qwen.py --input_dir input --output_dir output
-# Converted model: https://huggingface.co/hiyouga/Qwen-14B-Chat-LLaMAfied
+# Copyright 2024 the LlamaFactory team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
 import json
 import os
@@ -131,6 +141,11 @@ def save_config(input_dir: str, output_dir: str, torch_dtype: str):
 def llamafy_qwen(
     input_dir: str, output_dir: str, shard_size: Optional[str] = "2GB", save_safetensors: Optional[bool] = False
 ):
+    r"""
+    Converts the Qwen models in the same format as LLaMA2.
+    Usage: python llamafy_qwen.py --input_dir input --output_dir output
+    Converted model: https://huggingface.co/hiyouga/Qwen-14B-Chat-LLaMAfied
+    """
     try:
         os.makedirs(output_dir, exist_ok=False)
     except Exception as e:

scripts/loftq_init.py

@@ -1,7 +1,20 @@
 # coding=utf-8
-# Initializes LoRA weights with LoRA-fine-tuning-aware Quantization (LoftQ)
-# Usage: python loftq_init.py --model_name_or_path path_to_model --save_dir output_dir
-# Inspired by: https://github.com/huggingface/peft/blob/main/examples/loftq_finetuning/quantize_save_load.py
+# Copyright 2024 HuggingFace Inc. and the LlamaFactory team.
+#
+# This code is inspired by HuggingFace's PEFT library.
+# https://github.com/huggingface/peft/blob/v0.10.0/examples/loftq_finetuning/quantize_save_load.py
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
 import os
 from typing import TYPE_CHECKING, Optional
@@ -49,6 +62,10 @@ def quantize_loftq(
     lora_target: Optional[str] = "q_proj,v_proj",
     save_safetensors: Optional[bool] = False,
 ):
+    r"""
+    Initializes LoRA weights with LoRA-fine-tuning-aware Quantization (LoftQ)
+    Usage: python loftq_init.py --model_name_or_path path_to_model --save_dir output_dir
+    """
     tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)
     model = AutoModelForCausalLM.from_pretrained(model_name_or_path, trust_remote_code=True, torch_dtype="auto")
     loftq_config = LoftQConfig(loftq_bits=loftq_bits, loftq_iter=loftq_iter)

scripts/test_toolcall.py

@@ -1,3 +1,18 @@
+# coding=utf-8
+# Copyright 2024 the LlamaFactory team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
 import json
 import os
 from typing import Sequence