Datasets:

jescy525
/

cypher-sft-v3-sources

Error code:   DatasetGenerationError
Exception:    CastError
Message:      Couldn't cast
total_examples: int64
train_examples: int64
validation_examples: int64
train_split: double
source_documents: int64
chunking_enabled: bool
max_chunk_size: int64
task_id: string
is_resolved: bool
messages: list<item: struct<role: string, content: string>>
  child 0, item: struct<role: string, content: string>
      child 0, role: string
      child 1, content: string
to
{'task_id': Value('string'), 'is_resolved': Value('bool'), 'messages': List({'role': Value('string'), 'content': Value('string')})}
because column names don't match
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1779, in _prepare_split_single
                  for key, table in generator:
                                    ^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 609, in wrapped
                  for item in generator(*args, **kwargs):
                              ^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 299, in _generate_tables
                  self._cast_table(pa_table, json_field_paths=json_field_paths),
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 128, in _cast_table
                  pa_table = table_cast(pa_table, self.info.features.arrow_schema)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2321, in table_cast
                  return cast_table_to_schema(table, schema)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2249, in cast_table_to_schema
                  raise CastError(
              datasets.table.CastError: Couldn't cast
              total_examples: int64
              train_examples: int64
              validation_examples: int64
              train_split: double
              source_documents: int64
              chunking_enabled: bool
              max_chunk_size: int64
              task_id: string
              is_resolved: bool
              messages: list<item: struct<role: string, content: string>>
                child 0, item: struct<role: string, content: string>
                    child 0, role: string
                    child 1, content: string
              to
              {'task_id': Value('string'), 'is_resolved': Value('bool'), 'messages': List({'role': Value('string'), 'content': Value('string')})}
              because column names don't match
              
              The above exception was the direct cause of the following exception:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1342, in compute_config_parquet_and_info_response
                  parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
                                                                        ^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 907, in stream_convert_to_parquet
                  builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1646, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1832, in _prepare_split_single
                  raise DatasetGenerationError("An error occurred while generating the dataset") from e
              datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

task_id string	is_resolved bool	messages list
/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1/run_1/cve-2010-5312/2026-03-14__01-11-55/cve-2010-5312/cve-2010-5312.1-of-1.2026-03-14__01-11-55/agent-logs/last_mini_run.traj.json	true	[ { "role": "system", "content": "You are a helpful assistant that can interact with a computer.\n\nYour response must contain exactly ONE bash code block with ONE command (or commands connected with && or \|\|).\nInclude a THOUGHT section before your command where you explain your reasoning process.\nFormat yo...
/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1/run_2/cve-2010-5312/2026-03-14__01-11-55/cve-2010-5312/cve-2010-5312.1-of-1.2026-03-14__01-11-55/agent-logs/last_mini_run.traj.json	true	[ { "role": "system", "content": "You are a helpful assistant that can interact with a computer.\n\nYour response must contain exactly ONE bash code block with ONE command (or commands connected with && or \|\|).\nInclude a THOUGHT section before your command where you explain your reasoning process.\nFormat yo...
/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1/run_3/cve-2010-5312/2026-03-14__01-11-55/cve-2010-5312/cve-2010-5312.1-of-1.2026-03-14__01-11-55/agent-logs/last_mini_run.traj.json	true	[ { "role": "system", "content": "You are a helpful assistant that can interact with a computer.\n\nYour response must contain exactly ONE bash code block with ONE command (or commands connected with && or \|\|).\nInclude a THOUGHT section before your command where you explain your reasoning process.\nFormat yo...
"/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1(...TRUNCATED)	true	[{"role":"system","content":"You are a helpful assistant that can interact with a computer.\n\nYour (...TRUNCATED)
"/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1(...TRUNCATED)	true	[{"role":"system","content":"You are a helpful assistant that can interact with a computer.\n\nYour (...TRUNCATED)
"/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1(...TRUNCATED)	false	[{"role":"system","content":"You are a helpful assistant that can interact with a computer.\n\nYour (...TRUNCATED)
"/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1(...TRUNCATED)	false	[{"role":"system","content":"You are a helpful assistant that can interact with a computer.\n\nYour (...TRUNCATED)
"/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1(...TRUNCATED)	false	[{"role":"system","content":"You are a helpful assistant that can interact with a computer.\n\nYour (...TRUNCATED)
"/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1(...TRUNCATED)	true	[{"role":"system","content":"You are a helpful assistant that can interact with a computer.\n\nYour (...TRUNCATED)
"/mmu_nlp_hdd/luoxianzhen/sqzhou/reject_sampling/sample_datas/claude-opus-4.5/trainset_0313_part1-t1(...TRUNCATED)	false	[{"role":"system","content":"You are a helpful assistant that can interact with a computer.\n\nYour (...TRUNCATED)

End of preview.

cypher-sft-v3-sources

Aggregated cybersec sources for CYPHER SFT v3 training. Combines instruction-tuning corpora + CVE chats + phishing/malware + code vulns.

Disclaimer (Responsible Disclosure)

This bundle aggregates publicly available security research datasets for defensive purposes only: training detection systems, threat-classification models, and security research tools.

Do not use any artifact in this collection for offensive operations against systems you do not own or have explicit authorization to test. See individual source licenses in SOURCES.md.

This is an aggregation of 28 HuggingFace datasets, re-bundled here for reproducibility and convenience. Each source is preserved in its original layout under <owner>__<repo>/.

See SOURCES.md for the full per-source attribution table including original license, URL, and category.

How to use

from huggingface_hub import snapshot_download
path = snapshot_download(repo_id="jescy525/cypher-sft-v3-sources", repo_type="dataset")
# path/AlicanKiraz0__Cybersecurity-Dataset-Fenrir-v2.1/
# path/Trendyol__Trendyol-Cybersecurity-Instruction-Tuning-Dataset/
# ...

License

Multi-license — see SOURCES.md for per-dataset attribution

This re-bundled collection is released under Apache-2.0 for the metadata and aggregation layer only — each individual source retains its original license.

Downloads last month: 2,555

Total file size:

63.7 GB

cypher-sft-v3-sources

Disclaimer (Responsible Disclosure)

Contents

How to use

License