root
108 lines
6.7 KiB
Python
Executable File
108 lines
6.7 KiB
Python
Executable File
import json
|
|
import glob
|
|
from tokenizers import Tokenizer
|
|
from tokenizers.models import BPE
|
|
from tokenizers.trainers import BpeTrainer
|
|
from tokenizers.pre_tokenizers import ByteLevel
|
|
from transformers import PreTrainedTokenizerFast
|
|
|
|
SPECIAL_TOKENS = [
|
|
"<|endoftext|>",
|
|
"<|im_start|>",
|
|
"<|im_end|>",
|
|
"<|object_ref_start|>",
|
|
"<|object_ref_end|>",
|
|
"<|box_start|>",
|
|
"<|box_end|>",
|
|
"<|quad_start|>",
|
|
"<|quad_end|>",
|
|
"<|vision_start|>",
|
|
"<|vision_end|>",
|
|
"<|vision_pad|>",
|
|
"<|image_pad|>",
|
|
"<|video_pad|>",
|
|
"<tool_call>",
|
|
"</tool_call>",
|
|
"<|fim_prefix|>",
|
|
"<|fim_middle|>",
|
|
"<|fim_suffix|>",
|
|
"<|fim_pad|>",
|
|
"<|repo_name|>",
|
|
"<|file_sep|>",
|
|
"<tool_response>",
|
|
"</tool_response>",
|
|
"<think>",
|
|
"</think>"
|
|
]
|
|
|
|
ADDITIONAL_SPECIAL_TOKENS = [
|
|
"<|im_start|>",
|
|
"<|im_end|>",
|
|
"<|object_ref_start|>",
|
|
"<|object_ref_end|>",
|
|
"<|box_start|>",
|
|
"<|box_end|>",
|
|
"<|quad_start|>",
|
|
"<|quad_end|>",
|
|
"<|vision_start|>",
|
|
"<|vision_end|>",
|
|
"<|vision_pad|>",
|
|
"<|image_pad|>",
|
|
"<|video_pad|>"
|
|
]
|
|
|
|
|
|
def read_corpus(files, batch_size=1000):
|
|
for file_path in files:
|
|
with open(file_path, "r", encoding="utf-8") as f:
|
|
batch = []
|
|
for line in f:
|
|
data = json.loads(line)
|
|
batch.append(data["text"])
|
|
if len(batch) >= batch_size:
|
|
yield batch
|
|
batch = []
|
|
if batch:
|
|
yield batch
|
|
|
|
tokenizer = Tokenizer(BPE(unk_token=None))
|
|
tokenizer.pre_tokenizer = ByteLevel(add_prefix_space=False)
|
|
|
|
trainer = BpeTrainer(
|
|
vocab_size=151643,
|
|
min_frequency=2,
|
|
special_tokens=SPECIAL_TOKENS,
|
|
show_progress=True
|
|
)
|
|
|
|
corpus_files = glob.glob("corpus/*.jsonl")
|
|
tokenizer.train_from_iterator(
|
|
iterator=read_corpus(corpus_files),
|
|
trainer=trainer,
|
|
length=None,
|
|
)
|
|
|
|
fast_tokenizer = PreTrainedTokenizerFast(
|
|
tokenizer_object=tokenizer,
|
|
eos_token="<|im_end|>",
|
|
pad_token="<|endoftext|>",
|
|
additional_special_tokens=ADDITIONAL_SPECIAL_TOKENS,
|
|
add_bos_token=False,
|
|
add_prefix_space=False,
|
|
clean_up_tokenization_spaces=False,
|
|
errors="replace",
|
|
model_max_length=131072,
|
|
split_special_tokens=False,
|
|
unk_token=None,
|
|
bos_token=None,
|
|
)
|
|
|
|
CHAT_TEMPLATE = """{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}"""
|
|
|
|
fast_tokenizer.chat_template = CHAT_TEMPLATE
|
|
|
|
save_path = "weights/weights_tokenizer/hf_tokenizer_BBPE"
|
|
fast_tokenizer.save_pretrained(save_path)
|
|
|
|
print(f"Tokenizer saved to {save_path}")
|