Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Langboat/Mengzi3
/ functions
Functions
78 in github.com/Langboat/Mengzi3
⨍
Functions
78
◇
Types & classes
9
↓ 14 callers
Method
write
(self, sizes, doc_idx)
finetune_demo/plugins/indexed_dataset.py:385
↓ 9 callers
Method
exists
(path)
finetune_demo/plugins/indexed_dataset.py:217
↓ 7 callers
Function
data_file_path
(prefix_path)
finetune_demo/plugins/indexed_dataset.py:130
↓ 7 callers
Function
print_rank_0
If distributed is initialized, print only on rank 0.
finetune_demo/plugins/indexed_dataset.py:28
↓ 6 callers
Function
index_file_path
(prefix_path)
finetune_demo/plugins/indexed_dataset.py:126
↓ 4 callers
Function
read_longs
(f, n)
finetune_demo/plugins/indexed_dataset.py:97
↓ 4 callers
Function
write_longs
(f, a)
finetune_demo/plugins/indexed_dataset.py:103
↓ 2 callers
Method
__init__
(self, path)
finetune_demo/plugins/indexed_dataset.py:146
↓ 2 callers
Method
_do_init
(self, path, skip_warmup)
finetune_demo/plugins/indexed_dataset.py:487
↓ 2 callers
Function
_warmup_mmap_file
(path)
finetune_demo/plugins/indexed_dataset.py:351
↓ 2 callers
Method
check_index
(self, i)
finetune_demo/plugins/indexed_dataset.py:172
↓ 2 callers
Function
code
(dtype)
finetune_demo/plugins/indexed_dataset.py:119
↓ 2 callers
Method
read_data
(self, path)
finetune_demo/plugins/indexed_dataset.py:169
↓ 2 callers
Function
set_seed
(seed)
examples/base_streaming_gen.py:42
↓ 2 callers
Method
size
(self, index)
finetune_demo/plugins/indexed_dataset.py:213
↓ 1 callers
Function
__best_fitting_dtype
(vocab_size=None)
finetune_demo/plugins/indexed_dataset.py:37
↓ 1 callers
Method
_get_pointers
(sizes)
finetune_demo/plugins/indexed_dataset.py:374
↓ 1 callers
Method
add_item
(self, tensor)
finetune_demo/plugins/indexed_dataset.py:299
↓ 1 callers
Method
concat_encode
(self, fin, file_path, stop_token_ids)
finetune_demo/finetune.py:324
↓ 1 callers
Method
dtype
(self)
finetune_demo/plugins/indexed_dataset.py:454
↓ 1 callers
Method
end_document
(self)
finetune_demo/plugins/indexed_dataset.py:307
↓ 1 callers
Method
finalize
(self, index_file)
finetune_demo/plugins/indexed_dataset.py:335
↓ 1 callers
Function
generate
(inputs)
examples/base_streaming_gen.py:49
↓ 1 callers
Function
get_num_lines
(file_path)
finetune_demo/finetune.py:291
↓ 1 callers
Function
infer_dataset_impl
(path)
finetune_demo/plugins/indexed_dataset.py:45
↓ 1 callers
Function
main
()
finetune_demo/finetune.py:423
↓ 1 callers
Function
make_builder
(out_file, impl, vocab_size=None)
finetune_demo/plugins/indexed_dataset.py:63
↓ 1 callers
Function
parse_args
()
examples/base_streaming_gen.py:29
↓ 1 callers
Function
parse_args
()
finetune_demo/finetune.py:62
↓ 1 callers
Function
preprocess_data
(args, key, level, dataset_impl='mmap')
finetune_demo/finetune.py:385
↓ 1 callers
Method
read_index
(self, path)
finetune_demo/plugins/indexed_dataset.py:152
↓ 1 callers
Method
writer
(cls, path, dtype)
finetune_demo/plugins/indexed_dataset.py:362
Method
__del__
(self)
finetune_demo/plugins/indexed_dataset.py:176
Method
__del__
(self)
finetune_demo/plugins/indexed_dataset.py:449
Method
__del__
(self)
finetune_demo/plugins/indexed_dataset.py:500
Method
__enter__
(self)
finetune_demo/plugins/indexed_dataset.py:364
Method
__exit__
(self, exc_type, exc_val, exc_tb)
finetune_demo/plugins/indexed_dataset.py:402
Method
__getitem__
(self, idx)
finetune_demo/finetune.py:307
Method
__getitem__
(self, idx)
finetune_demo/plugins/indexed_dataset.py:181
Method
__getitem__
(self, idx)
finetune_demo/plugins/indexed_dataset.py:261
Method
__getitem__
(self, i)
finetune_demo/plugins/indexed_dataset.py:466
Method
__getitem__
(self, idx)
finetune_demo/plugins/indexed_dataset.py:509
Method
__getstate__
(self)
finetune_demo/plugins/indexed_dataset.py:481
Method
__init__
(self, indexed_dataset)
finetune_demo/finetune.py:301
Method
__init__
(self, path, max_length=4096)
finetune_demo/finetune.py:317
Method
__init__
(self, path)
finetune_demo/plugins/indexed_dataset.py:227
Method
__init__
(self, out_file, dtype=np.int32)
finetune_demo/plugins/indexed_dataset.py:290
Method
__init__
(self, path, skip_warmup=False)
finetune_demo/plugins/indexed_dataset.py:407
Method
__init__
(self, path, skip_warmup=False)
finetune_demo/plugins/indexed_dataset.py:472
Method
__init__
(self, out_file, dtype=np.int64)
finetune_demo/plugins/indexed_dataset.py:580
Method
__len__
(self)
finetune_demo/finetune.py:304
Method
__len__
(self)
finetune_demo/plugins/indexed_dataset.py:207
Method
__len__
(self)
finetune_demo/plugins/indexed_dataset.py:469
Method
__len__
(self)
finetune_demo/plugins/indexed_dataset.py:505
Method
__setstate__
(self, state)
finetune_demo/plugins/indexed_dataset.py:484
Method
add_doc
(self, tensor, sizes)
finetune_demo/plugins/indexed_dataset.py:591
Method
add_item
(self, tensor)
finetune_demo/plugins/indexed_dataset.py:586
Function
create_doc_idx
(sizes)
finetune_demo/plugins/indexed_dataset.py:134
Function
dataset_exists
(path, impl)
finetune_demo/plugins/indexed_dataset.py:90
Method
doc_idx
(self)
finetune_demo/plugins/indexed_dataset.py:462
Method
doc_idx
(self)
finetune_demo/plugins/indexed_dataset.py:560
Method
end_document
(self)
finetune_demo/plugins/indexed_dataset.py:597
Method
exists
(path)
finetune_demo/plugins/indexed_dataset.py:574
Method
finalize
(self, index_file)
finetune_demo/plugins/indexed_dataset.py:613
Method
get
Retrieves a single item from the dataset with the option to only return a portion of the item. get(idx) is the same as [idx] but get
finetune_demo/plugins/indexed_dataset.py:538
Function
get_available_dataset_impl
()
finetune_demo/plugins/indexed_dataset.py:41
Method
get_doc_idx
(self)
finetune_demo/plugins/indexed_dataset.py:563
Function
make_dataset
(path, impl, skip_warmup=False)
finetune_demo/plugins/indexed_dataset.py:71
Method
merge_file_
(self, another_file)
finetune_demo/plugins/indexed_dataset.py:310
Method
merge_file_
(self, another_file)
finetune_demo/plugins/indexed_dataset.py:600
Method
num_tokens
(self, index)
finetune_demo/plugins/indexed_dataset.py:210
Method
prefetch
(self, indices)
finetune_demo/plugins/indexed_dataset.py:236
Method
set_doc_idx
(self, doc_idx_)
finetune_demo/plugins/indexed_dataset.py:566
Method
sizes
(self)
finetune_demo/plugins/indexed_dataset.py:458
Method
sizes
(self)
finetune_demo/plugins/indexed_dataset.py:556
Method
supports_prefetch
(self)
finetune_demo/plugins/indexed_dataset.py:222
Method
supports_prefetch
(self)
finetune_demo/plugins/indexed_dataset.py:233
Method
supports_prefetch
(self)
finetune_demo/plugins/indexed_dataset.py:570