Dataset Viewer
The dataset viewer is not available for this split.
Cannot load the dataset split (in streaming mode) to extract the first rows.
Error code: StreamingRowsError
Exception: CastError
Message: Couldn't cast
format_version: int64
source_repo_id: string
source_revision: string
source_files: list<item: struct<path: string, sha256: string, size: int64>>
child 0, item: struct<path: string, sha256: string, size: int64>
child 0, path: string
child 1, sha256: string
child 2, size: int64
conversion: string
tensor_count: int64
patch_count: int64
tensors: list<item: struct<name: string, source_shard: string, shape: list<item: int64>, dtype: string, sha25 (... 98 chars omitted)
child 0, item: struct<name: string, source_shard: string, shape: list<item: int64>, dtype: string, sha256: string, (... 86 chars omitted)
child 0, name: string
child 1, source_shard: string
child 2, shape: list<item: int64>
child 0, item: int64
child 3, dtype: string
child 4, sha256: string
child 5, patches: list<item: struct<path: string, offset: int64, size: int64, sha256: string>>
child 0, item: struct<path: string, offset: int64, size: int64, sha256: string>
child 0, path: string
child 1, offset: int64
child 2, size: int64
child 3, sha256: string
shards: list<item: struct<path: string, prefix_base64: string, sha256: string, size: int64>>
child 0, item: struct<path: string, prefix_base64: string, sha256: string, size: int64>
child 0, path: string
child 1, prefix_base64: string
child 2, sha256: string
child 3, size: int64
<|im_start|>: int64
<|file_sep|>: int64
<|repo_name|>: int64
<tool_call>: int64
<|object_ref_end|>: int64
<|fim_pad|>: int64
<|quad_start|>: int64
<|vision_start|>: int64
<|video_pad|>: int64
<|image_pad|>: int64
<|fim_middle|>: int64
<|endoftext|>: int64
<|fim_prefix|>: int64
<|quad_end|>: int64
<|fim_suffix|>: int64
<|vision_pad|>: int64
<|object_ref_start|>: int64
<|box_end|>: int64
<|im_end|>: int64
<|vision_end|>: int64
</tool_call>: int64
<|box_start|>: int64
</EF>: int64
<EF>: int64
to
{'</EF>': Value('int64'), '</tool_call>': Value('int64'), '<EF>': Value('int64'), '<tool_call>': Value('int64'), '<|box_end|>': Value('int64'), '<|box_start|>': Value('int64'), '<|endoftext|>': Value('int64'), '<|file_sep|>': Value('int64'), '<|fim_middle|>': Value('int64'), '<|fim_pad|>': Value('int64'), '<|fim_prefix|>': Value('int64'), '<|fim_suffix|>': Value('int64'), '<|im_end|>': Value('int64'), '<|im_start|>': Value('int64'), '<|image_pad|>': Value('int64'), '<|object_ref_end|>': Value('int64'), '<|object_ref_start|>': Value('int64'), '<|quad_end|>': Value('int64'), '<|quad_start|>': Value('int64'), '<|repo_name|>': Value('int64'), '<|video_pad|>': Value('int64'), '<|vision_end|>': Value('int64'), '<|vision_pad|>': Value('int64'), '<|vision_start|>': Value('int64')}
because column names don't match
Traceback: Traceback (most recent call last):
File "/src/services/worker/src/worker/utils.py", line 149, in get_rows_or_raise
return get_rows(
dataset=dataset,
...<4 lines>...
column_names=column_names,
)
File "/src/libs/libcommon/src/libcommon/utils.py", line 272, in decorator
return func(*args, **kwargs)
File "/src/services/worker/src/worker/utils.py", line 129, in get_rows
rows_plus_one = list(itertools.islice(safe_iter(ds, dataset=dataset), rows_max_number + 1))
File "/src/services/worker/src/worker/utils.py", line 544, in safe_iter
yield from ds.decode(False) if ds.features else ds
File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 3052, in __iter__
for key, example in ex_iterable:
^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 2559, in __iter__
for key, pa_table in self._iter_arrow():
~~~~~~~~~~~~~~~~^^
File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 2584, in _iter_arrow
for key, pa_table in self.ex_iterable._iter_arrow():
~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^
File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 558, in _iter_arrow
for key, pa_table in iterator:
^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 440, in _iter_arrow
for key, pa_table in self.generate_tables_fn(**gen_kwags):
~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 361, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2381, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2309, in cast_table_to_schema
raise CastError(
...<3 lines>...
)
datasets.table.CastError: Couldn't cast
format_version: int64
source_repo_id: string
source_revision: string
source_files: list<item: struct<path: string, sha256: string, size: int64>>
child 0, item: struct<path: string, sha256: string, size: int64>
child 0, path: string
child 1, sha256: string
child 2, size: int64
conversion: string
tensor_count: int64
patch_count: int64
tensors: list<item: struct<name: string, source_shard: string, shape: list<item: int64>, dtype: string, sha25 (... 98 chars omitted)
child 0, item: struct<name: string, source_shard: string, shape: list<item: int64>, dtype: string, sha256: string, (... 86 chars omitted)
child 0, name: string
child 1, source_shard: string
child 2, shape: list<item: int64>
child 0, item: int64
child 3, dtype: string
child 4, sha256: string
child 5, patches: list<item: struct<path: string, offset: int64, size: int64, sha256: string>>
child 0, item: struct<path: string, offset: int64, size: int64, sha256: string>
child 0, path: string
child 1, offset: int64
child 2, size: int64
child 3, sha256: string
shards: list<item: struct<path: string, prefix_base64: string, sha256: string, size: int64>>
child 0, item: struct<path: string, prefix_base64: string, sha256: string, size: int64>
child 0, path: string
child 1, prefix_base64: string
child 2, sha256: string
child 3, size: int64
<|im_start|>: int64
<|file_sep|>: int64
<|repo_name|>: int64
<tool_call>: int64
<|object_ref_end|>: int64
<|fim_pad|>: int64
<|quad_start|>: int64
<|vision_start|>: int64
<|video_pad|>: int64
<|image_pad|>: int64
<|fim_middle|>: int64
<|endoftext|>: int64
<|fim_prefix|>: int64
<|quad_end|>: int64
<|fim_suffix|>: int64
<|vision_pad|>: int64
<|object_ref_start|>: int64
<|box_end|>: int64
<|im_end|>: int64
<|vision_end|>: int64
</tool_call>: int64
<|box_start|>: int64
</EF>: int64
<EF>: int64
to
{'</EF>': Value('int64'), '</tool_call>': Value('int64'), '<EF>': Value('int64'), '<tool_call>': Value('int64'), '<|box_end|>': Value('int64'), '<|box_start|>': Value('int64'), '<|endoftext|>': Value('int64'), '<|file_sep|>': Value('int64'), '<|fim_middle|>': Value('int64'), '<|fim_pad|>': Value('int64'), '<|fim_prefix|>': Value('int64'), '<|fim_suffix|>': Value('int64'), '<|im_end|>': Value('int64'), '<|im_start|>': Value('int64'), '<|image_pad|>': Value('int64'), '<|object_ref_end|>': Value('int64'), '<|object_ref_start|>': Value('int64'), '<|quad_end|>': Value('int64'), '<|quad_start|>': Value('int64'), '<|repo_name|>': Value('int64'), '<|video_pad|>': Value('int64'), '<|vision_end|>': Value('int64'), '<|vision_pad|>': Value('int64'), '<|vision_start|>': Value('int64')}
because column names don't matchNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
Exact historical Qwen2.5-7B critique-token Base reconstruction bundle
This is a public reconstruction bundle, NOT a standalone loadable model. Download Qwen/Qwen2.5-7B at d149729398750b98c0af14eb82c78cfe92750796. Use rebuild_critique_base.py from the experiment code to convert the source BF16 tensors to FP32 and apply the included exact byte patches. The bundle includes the historical tokenizer, config and original shard headers. All 339 source/target tensors were compared; the original source weight files were matched against the official fixed-revision HF LFS SHA256 values. Expected SHA256 values for every original target tensor and shard are recorded. The reconstruction script checks all output shard checksums before completion. No source file on the original CPU development machine or mounted storage is needed by the reconstruction script. No GPU is required for reconstruction. Keep enough disk space for the official ~15.2 GB model and reconstructed ~30.5 GB model. This is an initialization asset, not a trained FCP-scores checkpoint.
- Downloads last month
- 75