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

support function calling

Browse Source 
Former-commit-id: 66533b3f65babf2429c92c0f8fafe4eff5e0ff63
This commit is contained in:
hiyouga
2024-01-18 09:54:23 +08:00
parent f7329b1a0e
commit a423274fd9
67 changed files with 1239 additions and 1079 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llmtuner/train/__init__.py
View File

@@ -1 +1,4 @@
from llmtuner.train.tuner import export_model, run_exp
from .tuner import export_model, run_exp
__all__ = ["export_model", "run_exp"]

5
src/llmtuner/train/dpo/__init__.py
View File

@@ -1 +1,4 @@
from llmtuner.train.dpo.workflow import run_dpo
from .workflow import run_dpo
__all__ = ["run_dpo"]

2
src/llmtuner/train/dpo/trainer.py
View File

@@ -5,7 +5,7 @@ from transformers import BatchEncoding, Trainer
from trl import DPOTrainer
from trl.trainer.utils import disable_dropout_in_model
from llmtuner.extras.constants import IGNORE_INDEX
from ...extras.constants import IGNORE_INDEX
if TYPE_CHECKING:
from transformers import PreTrainedModel

21
src/llmtuner/train/dpo/workflow.py
View File

@@ -3,18 +3,18 @@
from typing import TYPE_CHECKING, Optional, List
from transformers import Seq2SeqTrainingArguments
from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
from llmtuner.extras.constants import IGNORE_INDEX
from llmtuner.extras.ploting import plot_loss
from llmtuner.hparams import ModelArguments
from llmtuner.model import load_model_and_tokenizer
from llmtuner.train.dpo.collator import DPODataCollatorWithPadding
from llmtuner.train.dpo.trainer import CustomDPOTrainer
from llmtuner.train.utils import create_modelcard_and_push, create_ref_model
from ...data import get_dataset, split_dataset
from ...extras.constants import IGNORE_INDEX
from ...extras.ploting import plot_loss
from ...hparams import ModelArguments
from ...model import load_model_and_tokenizer
from ...train.dpo.collator import DPODataCollatorWithPadding
from ...train.dpo.trainer import CustomDPOTrainer
from ...train.utils import create_modelcard_and_push, create_ref_model
if TYPE_CHECKING:
from transformers import TrainerCallback
from llmtuner.hparams import DataArguments, FinetuningArguments
from ...hparams import DataArguments, FinetuningArguments
def run_dpo(
@@ -24,9 +24,8 @@ def run_dpo(
finetuning_args: "FinetuningArguments",
callbacks: Optional[List["TrainerCallback"]] = None
):
dataset = get_dataset(model_args, data_args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train)
dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="rm")
dataset = get_dataset(model_args, data_args, tokenizer, training_args, stage="rm")
data_collator = DPODataCollatorWithPadding(
tokenizer=tokenizer,
pad_to_multiple_of=8,

5
src/llmtuner/train/ppo/__init__.py
View File

@@ -1 +1,4 @@
from llmtuner.train.ppo.workflow import run_ppo
from .workflow import run_ppo
__all__ = ["run_ppo"]

10
src/llmtuner/train/ppo/trainer.py
View File

@@ -13,15 +13,15 @@ from transformers.trainer_pt_utils import remove_dummy_checkpoint
from trl import PPOTrainer
from trl.core import PPODecorators, logprobs_from_logits
from llmtuner.extras.callbacks import LogCallback, FixValueHeadModelCallback
from llmtuner.extras.logging import get_logger
from llmtuner.extras.misc import AverageMeter, count_parameters, get_logits_processor
from llmtuner.train.ppo.utils import dump_layernorm, get_rewards_from_server, restore_layernorm, replace_model
from ...extras.callbacks import LogCallback, FixValueHeadModelCallback
from ...extras.logging import get_logger
from ...extras.misc import AverageMeter, count_parameters, get_logits_processor
from .utils import dump_layernorm, get_rewards_from_server, restore_layernorm, replace_model
if TYPE_CHECKING:
from transformers import Seq2SeqTrainingArguments, TrainerCallback
from trl import AutoModelForCausalLMWithValueHead
from llmtuner.hparams import ModelArguments, FinetuningArguments, GeneratingArguments
from ...hparams import ModelArguments, FinetuningArguments, GeneratingArguments
logger = get_logger(__name__)

2
src/llmtuner/train/ppo/utils.py
View File

@@ -2,7 +2,7 @@ import json
import torch
from typing import TYPE_CHECKING, Dict, List, Literal, Optional
from llmtuner.extras.packages import is_requests_available
from ...extras.packages import is_requests_available
if TYPE_CHECKING:
from transformers import PreTrainedModel

19
src/llmtuner/train/ppo/workflow.py
View File

@@ -7,17 +7,17 @@ from typing import TYPE_CHECKING, Optional, List
from transformers import DataCollatorWithPadding
from transformers.optimization import get_scheduler
from llmtuner.data import get_dataset, preprocess_dataset
from llmtuner.extras.callbacks import FixValueHeadModelCallback
from llmtuner.extras.misc import fix_valuehead_checkpoint
from llmtuner.extras.ploting import plot_loss
from llmtuner.model import load_model_and_tokenizer
from llmtuner.train.utils import create_ref_model, create_reward_model
from llmtuner.train.ppo.trainer import CustomPPOTrainer
from ...data import get_dataset
from ...extras.callbacks import FixValueHeadModelCallback
from ...extras.misc import fix_valuehead_checkpoint
from ...extras.ploting import plot_loss
from ...model import load_model_and_tokenizer
from ...train.utils import create_ref_model, create_reward_model
from ...train.ppo.trainer import CustomPPOTrainer
if TYPE_CHECKING:
from transformers import Seq2SeqTrainingArguments, TrainerCallback
from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments, GeneratingArguments
from ...hparams import ModelArguments, DataArguments, FinetuningArguments, GeneratingArguments
def run_ppo(
@@ -28,9 +28,8 @@ def run_ppo(
generating_args: "GeneratingArguments",
callbacks: Optional[List["TrainerCallback"]] = None
):
dataset = get_dataset(model_args, data_args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train, add_valuehead=True)
dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="ppo")
dataset = get_dataset(model_args, data_args, tokenizer, training_args, stage="ppo")
tokenizer.padding_side = "left" # use left-padding in generation while using right-padding in training
data_collator = DataCollatorWithPadding(tokenizer=tokenizer)

5
src/llmtuner/train/pt/__init__.py
View File

@@ -1 +1,4 @@
from llmtuner.train.pt.workflow import run_pt
from .workflow import run_pt
__all__ = ["run_pt"]

13
src/llmtuner/train/pt/workflow.py
View File

@@ -4,14 +4,14 @@ import math
from typing import TYPE_CHECKING, Optional, List
from transformers import DataCollatorForLanguageModeling, Trainer
from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
from llmtuner.extras.ploting import plot_loss
from llmtuner.model import load_model_and_tokenizer
from llmtuner.train.utils import create_modelcard_and_push
from ...data import get_dataset, split_dataset
from ...extras.ploting import plot_loss
from ...model import load_model_and_tokenizer
from ...train.utils import create_modelcard_and_push
if TYPE_CHECKING:
from transformers import Seq2SeqTrainingArguments, TrainerCallback
from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments
from ...hparams import ModelArguments, DataArguments, FinetuningArguments
def run_pt(
@@ -21,9 +21,8 @@ def run_pt(
finetuning_args: "FinetuningArguments",
callbacks: Optional[List["TrainerCallback"]] = None
):
dataset = get_dataset(model_args, data_args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train)
dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="pt")
dataset = get_dataset(model_args, data_args, tokenizer, training_args, stage="pt")
data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
# Initialize our Trainer

5
src/llmtuner/train/rm/__init__.py
View File

@@ -1 +1,4 @@
from llmtuner.train.rm.workflow import run_rm
from .workflow import run_rm
__all__ = ["run_rm"]

2
src/llmtuner/train/rm/trainer.py
View File

@@ -4,7 +4,7 @@ import torch
from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, Union
from transformers import Trainer
from llmtuner.extras.logging import get_logger
from ...extras.logging import get_logger
if TYPE_CHECKING:
from transformers.trainer import PredictionOutput

23
src/llmtuner/train/rm/workflow.py
View File

@@ -3,19 +3,19 @@
from typing import TYPE_CHECKING, Optional, List
from transformers import Seq2SeqTrainingArguments
from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
from llmtuner.extras.callbacks import FixValueHeadModelCallback
from llmtuner.extras.misc import fix_valuehead_checkpoint
from llmtuner.extras.ploting import plot_loss
from llmtuner.model import load_model_and_tokenizer
from llmtuner.train.rm.collator import PairwiseDataCollatorWithPadding
from llmtuner.train.rm.metric import compute_accuracy
from llmtuner.train.rm.trainer import PairwiseTrainer
from llmtuner.train.utils import create_modelcard_and_push
from ...data import get_dataset, split_dataset
from ...extras.callbacks import FixValueHeadModelCallback
from ...extras.misc import fix_valuehead_checkpoint
from ...extras.ploting import plot_loss
from ...model import load_model_and_tokenizer
from ...train.rm.collator import PairwiseDataCollatorWithPadding
from ...train.rm.metric import compute_accuracy
from ...train.rm.trainer import PairwiseTrainer
from ...train.utils import create_modelcard_and_push
if TYPE_CHECKING:
from transformers import TrainerCallback
from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments
from ...hparams import ModelArguments, DataArguments, FinetuningArguments
def run_rm(
@@ -25,9 +25,8 @@ def run_rm(
finetuning_args: "FinetuningArguments",
callbacks: Optional[List["TrainerCallback"]] = None
):
dataset = get_dataset(model_args, data_args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train, add_valuehead=True)
dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="rm")
dataset = get_dataset(model_args, data_args, tokenizer, training_args, stage="rm")
data_collator = PairwiseDataCollatorWithPadding(tokenizer, pad_to_multiple_of=8)
# Update arguments

5
src/llmtuner/train/sft/__init__.py
View File

@@ -1 +1,4 @@
from llmtuner.train.sft.workflow import run_sft
from .workflow import run_sft
__all__ = ["run_sft"]

4
src/llmtuner/train/sft/metric.py
View File

@@ -2,8 +2,8 @@ import numpy as np
from dataclasses import dataclass
from typing import TYPE_CHECKING, Dict, Sequence, Tuple, Union
from llmtuner.extras.constants import IGNORE_INDEX
from llmtuner.extras.packages import (
from ...extras.constants import IGNORE_INDEX
from ...extras.packages import (
is_jieba_available, is_nltk_available, is_rouge_available
)

4
src/llmtuner/train/sft/trainer.py
View File

@@ -6,8 +6,8 @@ import torch.nn as nn
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
from transformers import Seq2SeqTrainer
from llmtuner.extras.constants import IGNORE_INDEX
from llmtuner.extras.logging import get_logger
from ...extras.constants import IGNORE_INDEX
from ...extras.logging import get_logger
if TYPE_CHECKING:
from transformers.trainer import PredictionOutput

22
src/llmtuner/train/sft/workflow.py
View File

@@ -3,18 +3,19 @@
from typing import TYPE_CHECKING, Optional, List
from transformers import DataCollatorForSeq2Seq, Seq2SeqTrainingArguments
from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
from llmtuner.extras.constants import IGNORE_INDEX
from llmtuner.extras.misc import get_logits_processor
from llmtuner.extras.ploting import plot_loss
from llmtuner.model import load_model_and_tokenizer
from llmtuner.train.sft.metric import ComputeMetrics
from llmtuner.train.sft.trainer import CustomSeq2SeqTrainer
from llmtuner.train.utils import create_modelcard_and_push
from ...data import get_dataset, split_dataset
from ...extras.constants import IGNORE_INDEX
from ...extras.misc import get_logits_processor
from ...extras.ploting import plot_loss
from ...model import load_model_and_tokenizer
from ...train.sft.metric import ComputeMetrics
from ...train.sft.trainer import CustomSeq2SeqTrainer
from ...train.utils import create_modelcard_and_push
if TYPE_CHECKING:
from transformers import TrainerCallback
from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments, GeneratingArguments
from ...hparams import ModelArguments, DataArguments, FinetuningArguments, GeneratingArguments
def run_sft(
@@ -25,9 +26,8 @@ def run_sft(
generating_args: "GeneratingArguments",
callbacks: Optional[List["TrainerCallback"]] = None
):
dataset = get_dataset(model_args, data_args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train)
dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="sft")
dataset = get_dataset(model_args, data_args, tokenizer, training_args, stage="sft")
if training_args.predict_with_generate:
tokenizer.padding_side = "left" # use left-padding in generation

17
src/llmtuner/train/tuner.py
View File

@@ -2,14 +2,15 @@ import torch
from typing import TYPE_CHECKING, Any, Dict, List, Optional
from transformers import PreTrainedModel
from llmtuner.extras.callbacks import LogCallback
from llmtuner.extras.logging import get_logger
from llmtuner.model import get_train_args, get_infer_args, load_model_and_tokenizer
from llmtuner.train.pt import run_pt
from llmtuner.train.sft import run_sft
from llmtuner.train.rm import run_rm
from llmtuner.train.ppo import run_ppo
from llmtuner.train.dpo import run_dpo
from ..extras.callbacks import LogCallback
from ..extras.logging import get_logger
from ..hparams import get_train_args, get_infer_args
from ..model import load_model_and_tokenizer
from .pt import run_pt
from .sft import run_sft
from .rm import run_rm
from .ppo import run_ppo
from .dpo import run_dpo
if TYPE_CHECKING:
from transformers import TrainerCallback

8
src/llmtuner/train/utils.py
View File

@@ -1,15 +1,15 @@
import torch
from typing import TYPE_CHECKING, Optional, Union
from llmtuner.extras.logging import get_logger
from llmtuner.hparams import ModelArguments, FinetuningArguments
from llmtuner.model import get_modelcard_args, load_model_and_tokenizer, load_valuehead_params
from ..extras.logging import get_logger
from ..hparams import ModelArguments, FinetuningArguments
from ..model import get_modelcard_args, load_model_and_tokenizer, load_valuehead_params
if TYPE_CHECKING:
from transformers import Seq2SeqTrainingArguments, Trainer
from transformers.modeling_utils import PreTrainedModel
from trl import AutoModelForCausalLMWithValueHead
from llmtuner.hparams import DataArguments
from ..hparams import DataArguments
logger = get_logger(__name__)