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

support system column #1765

Browse Source 
Former-commit-id: f425584a511c5e42bae8b3ba090eaa898b28adad
This commit is contained in:
hiyouga
2023-12-12 19:45:59 +08:00
parent c27675f70d
commit 934d00ea1e
14 changed files with 42 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/chat/chat_model.py
View File

@@ -30,7 +30,6 @@ class ChatModel:
self.tokenizer.padding_side = "left" if self.can_generate else "right"
self.model = dispatch_model(self.model)
self.template = get_template_and_fix_tokenizer(data_args.template, self.tokenizer)
self.system_prompt = data_args.system_prompt
def _process_args(
self,
@@ -39,7 +38,6 @@ class ChatModel:
system: Optional[str] = None,
**input_kwargs
) -> Tuple[Dict[str, Any], int]:
system = system or self.system_prompt
prompt, _ = self.template.encode_oneturn(
tokenizer=self.tokenizer, query=query, resp="", history=history, system=system
)

16
src/llmtuner/data/loader.py
View File

@@ -83,7 +83,7 @@ def get_dataset(
streaming=(data_args.streaming and (dataset_attr.load_from != "file"))
)
if data_args.streaming and (dataset_attr.load_from == "file"):
if data_args.streaming and (dataset_attr.load_from == "file"): # faster than specifying streaming=True
dataset = dataset.to_iterable_dataset() # TODO: add num shards parameter
if max_samples is not None: # truncate dataset
@@ -91,8 +91,8 @@ def get_dataset(
def convert_format(examples: Dict[str, List[Any]]) -> Dict[str, List[Any]]:
# convert dataset from sharegpt format to alpaca format
outputs = {"prompt": [], "query": [], "response": [], "history": []}
for msg_list in examples[dataset_attr.messages]:
outputs = {"prompt": [], "query": [], "response": [], "history": [], "system": []}
for i, msg_list in enumerate(examples[dataset_attr.messages]):
msg_list = msg_list[:len(msg_list) // 2 * 2] # should be multiples of 2
if len(msg_list) == 0:
continue
@@ -116,6 +116,7 @@ def get_dataset(
outputs["query"].append("")
outputs["response"].append(msg_pairs[-1][1])
outputs["history"].append(msg_pairs[:-1])
outputs["system"].append(examples[dataset_attr.system][i] if dataset_attr.system else "")
return outputs
@@ -136,17 +137,10 @@ def get_dataset(
**kwargs
)
else:
for column_name in ["prompt", "query", "response", "history"]: # align dataset
for column_name in ["prompt", "query", "response", "history", "system"]: # align dataset
if getattr(dataset_attr, column_name) and getattr(dataset_attr, column_name) != column_name:
dataset = dataset.rename_column(getattr(dataset_attr, column_name), column_name)
if dataset_attr.system_prompt: # add system prompt
system_prompt = dataset_attr.system_prompt
if data_args.streaming:
dataset = dataset.map(lambda _: {"system": system_prompt})
else:
dataset = dataset.add_column("system", [system_prompt] * len(dataset))
all_datasets.append(dataset)
if len(data_args.dataset_list) == 1:

14
src/llmtuner/hparams/data_args.py
View File

@@ -17,7 +17,6 @@ class DatasetAttr:
load_from: Literal["hf_hub", "ms_hub", "script", "file"]
dataset_name: Optional[str] = None
dataset_sha1: Optional[str] = None
system_prompt: Optional[str] = None
subset: Optional[str] = None
folder: Optional[str] = None
ranking: Optional[bool] = False
@@ -30,6 +29,7 @@ class DatasetAttr:
messages: Optional[str] = "conversations"
role: Optional[str] = "from"
content: Optional[str] = "value"
system: Optional[str] = None
def __repr__(self) -> str:
return self.dataset_name
@@ -104,10 +104,6 @@ class DataArguments:
default=True,
metadata={"help": "Whether to ignore the tokens corresponding to padded labels in the loss computation or not."}
)
system_prompt: Optional[str] = field(
default=None,
metadata={"help": "System prompt to add before the user query. Use `|` to separate multiple prompts in training."}
)
val_size: Optional[float] = field(
default=0,
metadata={"help": "Size of the development set, should be an integer or a float in range `[0,1)`."}
@@ -145,15 +141,11 @@ class DataArguments:
raise ValueError("Cannot open {} due to {}.".format(os.path.join(self.dataset_dir, DATA_CONFIG), str(err)))
dataset_info = None
prompt_list = self.system_prompt.split("|") if self.system_prompt else [None]
prompt_list = prompt_list * (len(dataset_names) // len(prompt_list))
assert len(prompt_list) == len(dataset_names), "Number of system prompts should be equal to datasets or 1."
if self.interleave_probs is not None:
self.interleave_probs = [float(prob.strip()) for prob in self.interleave_probs.split(",")]
self.dataset_list: List[DatasetAttr] = []
for i, name in enumerate(dataset_names):
for name in dataset_names:
if name not in dataset_info:
raise ValueError("Undefined dataset {} in {}.".format(name, DATA_CONFIG))
@@ -191,10 +183,10 @@ class DataArguments:
dataset_attr.messages = dataset_info[name]["columns"].get("messages", None)
dataset_attr.role = dataset_info[name]["columns"].get("role", None)
dataset_attr.content = dataset_info[name]["columns"].get("content", None)
dataset_attr.system = dataset_info[name]["columns"].get("system", None)
dataset_attr.subset = dataset_info[name].get("subset", None)
dataset_attr.folder = dataset_info[name].get("folder", None)
dataset_attr.ranking = dataset_info[name].get("ranking", False)
dataset_attr.formatting = dataset_info[name].get("formatting", "alpaca")
dataset_attr.system_prompt = prompt_list[i]
self.dataset_list.append(dataset_attr)

2
src/llmtuner/model/loader.py
View File

@@ -217,7 +217,7 @@ def load_model_and_tokenizer(
# Prepare model for inference
if not is_trainable:
model.requires_grad_(False) # fix all model params
model = model.to(model_args.compute_dtype) if model_args.quantization_bit is None else model
model = model.to(model_args.compute_dtype) if not getattr(model, "quantization_method", None) else model
model.eval()
else:
model.train()

1
src/llmtuner/webui/chatter.py
View File

@@ -77,7 +77,6 @@ class WebChatModel(ChatModel):
finetuning_type=get("top.finetuning_type"),
quantization_bit=int(get("top.quantization_bit")) if get("top.quantization_bit") in ["8", "4"] else None,
template=get("top.template"),
system_prompt=get("top.system_prompt"),
flash_attn=get("top.flash_attn"),
shift_attn=get("top.shift_attn"),
rope_scaling=get("top.rope_scaling") if get("top.rope_scaling") in ["linear", "dynamic"] else None

15
src/llmtuner/webui/components/top.py
View File

@@ -25,16 +25,13 @@ def create_top() -> Dict[str, "Component"]:
with gr.Accordion(label="Advanced config", open=False) as advanced_tab:
with gr.Row():
quantization_bit = gr.Dropdown(choices=["none", "8", "4"], value="none", scale=1)
template = gr.Dropdown(choices=list(templates.keys()), value="default", scale=1)
system_prompt = gr.Textbox(scale=2)
quantization_bit = gr.Dropdown(choices=["none", "8", "4"], value="none")
template = gr.Dropdown(choices=list(templates.keys()), value="default")
rope_scaling = gr.Radio(choices=["none", "linear", "dynamic"], value="none")
with gr.Accordion(label="Model config (LLaMA only)", open=False) as llama_tab:
with gr.Row():
with gr.Column():
flash_attn = gr.Checkbox(value=False)
shift_attn = gr.Checkbox(value=False)
rope_scaling = gr.Radio(choices=["none", "linear", "dynamic"], value="none")
model_name.change(
list_checkpoint, [model_name, finetuning_type], [checkpoints], queue=False
@@ -66,9 +63,7 @@ def create_top() -> Dict[str, "Component"]:
advanced_tab=advanced_tab,
quantization_bit=quantization_bit,
template=template,
system_prompt=system_prompt,
llama_tab=llama_tab,
rope_scaling=rope_scaling,
flash_attn=flash_attn,
shift_attn=shift_attn,
rope_scaling=rope_scaling
shift_attn=shift_attn
)

24
src/llmtuner/webui/locales.py
View File

@@ -77,22 +77,12 @@ LOCALES = {
"info": "构建提示词时使用的模板"
}
},
"system_prompt": {
"rope_scaling": {
"en": {
"label": "System prompt (optional)",
"info": "A sequence used as the default system prompt."
"label": "RoPE scaling"
},
"zh": {
"label": "系统提示词（非必填）",
"info": "默认使用的系统提示词"
}
},
"llama_tab": {
"en": {
"label": "Model configurations (LLaMA only)"
},
"zh": {
"label": "模型设置（仅LLaMA）"
"label": "RoPE 插值方法"
}
},
"flash_attn": {
@@ -111,14 +101,6 @@ LOCALES = {
"label": "使用 shift short attention (S^2-Attn)"
}
},
"rope_scaling": {
"en": {
"label": "RoPE scaling"
},
"zh": {
"label": "RoPE 插值方法"
}
},
"training_stage": {
"en": {
"label": "Stage",

1
src/llmtuner/webui/manager.py
View File

@@ -25,7 +25,6 @@ class Manager:
self.all_elems["top"]["finetuning_type"],
self.all_elems["top"]["quantization_bit"],
self.all_elems["top"]["template"],
self.all_elems["top"]["system_prompt"],
self.all_elems["top"]["flash_attn"],
self.all_elems["top"]["shift_attn"],
self.all_elems["top"]["rope_scaling"]

2
src/llmtuner/webui/runner.py
View File

@@ -102,7 +102,6 @@ class Runner:
finetuning_type=get("top.finetuning_type"),
quantization_bit=int(get("top.quantization_bit")) if get("top.quantization_bit") in ["8", "4"] else None,
template=get("top.template"),
system_prompt=get("top.system_prompt"),
flash_attn=get("top.flash_attn"),
shift_attn=get("top.shift_attn"),
rope_scaling=get("top.rope_scaling") if get("top.rope_scaling") in ["linear", "dynamic"] else None,
@@ -176,7 +175,6 @@ class Runner:
finetuning_type=get("top.finetuning_type"),
quantization_bit=int(get("top.quantization_bit")) if get("top.quantization_bit") in ["8", "4"] else None,
template=get("top.template"),
system_prompt=get("top.system_prompt"),
flash_attn=get("top.flash_attn"),
shift_attn=get("top.shift_attn"),
rope_scaling=get("top.rope_scaling") if get("top.rope_scaling") in ["linear", "dynamic"] else None,