ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

format style

Browse Source 
Former-commit-id: 53b683531b83cd1d19de97c6565f16c1eca6f5e1
This commit is contained in:
hiyouga
2024-01-20 20:15:56 +08:00
parent 1750218057
commit 66e0e651b9
73 changed files with 1492 additions and 2325 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
src/llmtuner/hparams/model_args.py
View File

@@ -1,5 +1,5 @@
from typing import Any, Dict, Literal, Optional
from dataclasses import asdict, dataclass, field
from typing import Any, Dict, Literal, Optional
@dataclass
@@ -11,108 +11,82 @@ class ModelArguments:
metadata={"help": "Path to the model weight or identifier from huggingface.co/models or modelscope.cn/models."}
)
adapter_name_or_path: Optional[str] = field(
default=None,
metadata={"help": "Path to the adapter weight or identifier from huggingface.co/models."}
default=None, metadata={"help": "Path to the adapter weight or identifier from huggingface.co/models."}
)
cache_dir: Optional[str] = field(
default=None,
metadata={"help": "Where to store the pre-trained models downloaded from huggingface.co or modelscope.cn."}
metadata={"help": "Where to store the pre-trained models downloaded from huggingface.co or modelscope.cn."},
)
use_fast_tokenizer: Optional[bool] = field(
default=False,
metadata={"help": "Whether or not to use one of the fast tokenizer (backed by the tokenizers library)."}
metadata={"help": "Whether or not to use one of the fast tokenizer (backed by the tokenizers library)."},
)
resize_vocab: Optional[bool] = field(
default=False,
metadata={"help": "Whether or not to resize the tokenizer vocab and the embedding layers."}
default=False, metadata={"help": "Whether or not to resize the tokenizer vocab and the embedding layers."}
)
split_special_tokens: Optional[bool] = field(
default=False,
metadata={"help": "Whether or not the special tokens should be split during the tokenization process."}
metadata={"help": "Whether or not the special tokens should be split during the tokenization process."},
)
model_revision: Optional[str] = field(
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."}
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
quantization_bit: Optional[int] = field(
default=None,
metadata={"help": "The number of bits to quantize the model."}
default=None, metadata={"help": "The number of bits to quantize the model."}
)
quantization_type: Optional[Literal["fp4", "nf4"]] = field(
default="nf4",
metadata={"help": "Quantization data type to use in int4 training."}
default="nf4", metadata={"help": "Quantization data type to use in int4 training."}
)
double_quantization: Optional[bool] = field(
default=True,
metadata={"help": "Whether or not to use double quantization in int4 training."}
default=True, metadata={"help": "Whether or not to use double quantization in int4 training."}
)
rope_scaling: Optional[Literal["linear", "dynamic"]] = field(
default=None,
metadata={"help": "Which scaling strategy should be adopted for the RoPE embeddings."}
default=None, metadata={"help": "Which scaling strategy should be adopted for the RoPE embeddings."}
)
flash_attn: Optional[bool] = field(
default=False,
metadata={"help": "Enable FlashAttention-2 for faster training."}
default=False, metadata={"help": "Enable FlashAttention-2 for faster training."}
)
shift_attn: Optional[bool] = field(
default=False,
metadata={"help": "Enable shift short attention (S^2-Attn) proposed by LongLoRA."}
default=False, metadata={"help": "Enable shift short attention (S^2-Attn) proposed by LongLoRA."}
)
use_unsloth: Optional[bool] = field(
default=False,
metadata={"help": "Whether or not to use unsloth's optimization for the LoRA training."}
default=False, metadata={"help": "Whether or not to use unsloth's optimization for the LoRA training."}
)
disable_gradient_checkpointing: Optional[bool] = field(
default=False,
metadata={"help": "Whether or not to disable gradient checkpointing."}
default=False, metadata={"help": "Whether or not to disable gradient checkpointing."}
)
upcast_layernorm: Optional[bool] = field(
default=False,
metadata={"help": "Whether or not to upcast the layernorm weights in fp32."}
default=False, metadata={"help": "Whether or not to upcast the layernorm weights in fp32."}
)
upcast_lmhead_output: Optional[bool] = field(
default=False,
metadata={"help": "Whether or not to upcast the output of lm_head in fp32."}
)
hf_hub_token: Optional[str] = field(
default=None,
metadata={"help": "Auth token to log in with Hugging Face Hub."}
)
ms_hub_token: Optional[str] = field(
default=None,
metadata={"help": "Auth token to log in with ModelScope Hub."}
default=False, metadata={"help": "Whether or not to upcast the output of lm_head in fp32."}
)
hf_hub_token: Optional[str] = field(default=None, metadata={"help": "Auth token to log in with Hugging Face Hub."})
ms_hub_token: Optional[str] = field(default=None, metadata={"help": "Auth token to log in with ModelScope Hub."})
export_dir: Optional[str] = field(
default=None,
metadata={"help": "Path to the directory to save the exported model."}
default=None, metadata={"help": "Path to the directory to save the exported model."}
)
export_size: Optional[int] = field(
default=1,
metadata={"help": "The file shard size (in GB) of the exported model."}
default=1, metadata={"help": "The file shard size (in GB) of the exported model."}
)
export_quantization_bit: Optional[int] = field(
default=None,
metadata={"help": "The number of bits to quantize the exported model."}
default=None, metadata={"help": "The number of bits to quantize the exported model."}
)
export_quantization_dataset: Optional[str] = field(
default=None,
metadata={"help": "Path to the dataset or dataset name to use in quantizing the exported model."}
default=None, metadata={"help": "Path to the dataset or dataset name to use in quantizing the exported model."}
)
export_quantization_nsamples: Optional[int] = field(
default=128,
metadata={"help": "The number of samples used for quantization."}
default=128, metadata={"help": "The number of samples used for quantization."}
)
export_quantization_maxlen: Optional[int] = field(
default=1024,
metadata={"help": "The maximum length of the model inputs used for quantization."}
default=1024, metadata={"help": "The maximum length of the model inputs used for quantization."}
)
export_legacy_format: Optional[bool] = field(
default=False,
metadata={"help": "Whether or not to save the `.bin` files instead of `.safetensors`."}
default=False, metadata={"help": "Whether or not to save the `.bin` files instead of `.safetensors`."}
)
export_hub_model_id: Optional[str] = field(
default=None,
metadata={"help": "The name of the repository if push the model to the Hugging Face hub."}
default=None, metadata={"help": "The name of the repository if push the model to the Hugging Face hub."}
)
def __post_init__(self):
@@ -122,7 +96,7 @@ class ModelArguments:
if self.split_special_tokens and self.use_fast_tokenizer:
raise ValueError("`split_special_tokens` is only supported for slow tokenizers.")
if self.adapter_name_or_path is not None: # support merging multiple lora weights
if self.adapter_name_or_path is not None: # support merging multiple lora weights
self.adapter_name_or_path = [path.strip() for path in self.adapter_name_or_path.split(",")]
assert self.quantization_bit in [None, 8, 4], "We only accept 4-bit or 8-bit quantization."