Spaces:

---

Intel

/

low_bit_open_llm_leaderboard

like 218

Running

Pipeline Failure Report

Model: Quazim0t0/Escarda-86M-Base
Quantization Scheme: INT4 (W4A16)
Failed Phase: quantize
Run ID: Escarda-86M-Base-AutoRound-W4A16-RTN
Error Category: dataset_error

Full Error Log

Map:   0%|          | 0/10000 [00:00<?, ? examples/s]
Map: 100%|██████████| 10000/10000 [01:56<00:00, 85.97 examples/s]

Filter:   0%|          | 0/10000 [00:00<?, ? examples/s]
Filter: 100%|██████████| 10000/10000 [00:03<00:00, 2524.01 examples/s]
Process ForkProcess-1:
Traceback (most recent call last):
  File "/root/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/root/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/root/.venv/lib/python3.12/site-packages/auto_round/calib_dataset.py", line 889, in _get_dataset_impl
    dataset.set_format(type="torch", columns=["input_ids", "attention_mask"])
  File "/root/.venv/lib/python3.12/site-packages/datasets/fingerprint.py", line 468, in wrapper
    out = func(dataset, *args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.venv/lib/python3.12/site-packages/datasets/arrow_dataset.py", line 2916, in set_format
    raise ValueError(
ValueError: Columns ['attention_mask'] not in the dataset. Current columns in the dataset: ['text', 'meta', 'input_ids']
2026-07-06 09:43:22 WARNING calib_dataset.py L995: Subprocess dataset preprocessing failed (Dataset preprocessing subprocess exited with code 1), falling back to in-process mode.
09:43:22 [INFO] HTTP Request: HEAD https://huggingface.co/datasets/NeelNanda/pile-10k/resolve/main/README.md "HTTP/1.1 307 Temporary Redirect"
09:43:22 [INFO] HTTP Request: HEAD https://huggingface.co/api/resolve-cache/datasets/NeelNanda/pile-10k/127bfedcd5047750df5ccf3a12979a47bfa0bafa/README.md "HTTP/1.1 200 OK"
09:43:23 [INFO] HTTP Request: HEAD https://huggingface.co/datasets/NeelNanda/pile-10k/resolve/127bfedcd5047750df5ccf3a12979a47bfa0bafa/pile-10k.py "HTTP/1.1 404 Not Found"
09:43:23 [INFO] HTTP Request: HEAD https://s3.amazonaws.com/datasets.huggingface.co/datasets/datasets/NeelNanda/pile-10k/NeelNanda/pile-10k.py "HTTP/1.1 404 Not Found"
09:43:23 [INFO] HTTP Request: GET https://huggingface.co/api/datasets/NeelNanda/pile-10k/revision/127bfedcd5047750df5ccf3a12979a47bfa0bafa "HTTP/1.1 200 OK"
09:43:23 [INFO] HTTP Request: HEAD https://huggingface.co/datasets/NeelNanda/pile-10k/resolve/127bfedcd5047750df5ccf3a12979a47bfa0bafa/.huggingface.yaml "HTTP/1.1 404 Not Found"
09:43:23 [INFO] HTTP Request: GET https://datasets-server.huggingface.co/info?dataset=NeelNanda/pile-10k "HTTP/1.1 200 OK"
09:43:24 [INFO] HTTP Request: GET https://huggingface.co/api/datasets/NeelNanda/pile-10k/tree/127bfedcd5047750df5ccf3a12979a47bfa0bafa/data?recursive=true&expand=false "HTTP/1.1 200 OK"
09:43:24 [INFO] HTTP Request: GET https://huggingface.co/api/datasets/NeelNanda/pile-10k/tree/127bfedcd5047750df5ccf3a12979a47bfa0bafa?recursive=false&expand=false "HTTP/1.1 200 OK"
09:43:24 [ERROR] Quantization failed: Columns ['attention_mask'] not in the dataset. Current columns in the dataset: ['text', 'meta', 'input_ids']
Traceback (most recent call last):
  File "/root/_work/1/s/auto_quant/phases/quantize.py", line 380, in <module>
    quantize(args)
  File "/root/_work/1/s/auto_quant/phases/quantize.py", line 279, in quantize
    autoround.quantize()
  File "/root/.venv/lib/python3.12/site-packages/auto_round/compressors/data_driven.py", line 1149, in quantize
    return self._quantize_impl()
           ^^^^^^^^^^^^^^^^^^^^^
  File "/root/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/root/.venv/lib/python3.12/site-packages/auto_round/compressors/data_driven.py", line 1175, in _quantize_impl
    self._quant_rtn_with_imatrix()
  File "/root/.venv/lib/python3.12/site-packages/auto_round/compressors/data_driven.py", line 1093, in _quant_rtn_with_imatrix
    self._calibration_state.ensure_dataloader(self.model_context, self.seed)
  File "/root/.venv/lib/python3.12/site-packages/auto_round/calibration/state.py", line 140, in ensure_dataloader
    self.dataloader = get_dataloader(
                      ^^^^^^^^^^^^^^^
  File "/root/.venv/lib/python3.12/site-packages/auto_round/calib_dataset.py", line 1045, in get_dataloader
    dataset_final = get_dataset(tokenizer, seqlen, dataset_name, seed, nsamples)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.venv/lib/python3.12/site-packages/auto_round/calib_dataset.py", line 999, in get_dataset
    return _get_dataset_impl(tokenizer, seqlen, dataset_name, seed, nsamples)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.venv/lib/python3.12/site-packages/auto_round/calib_dataset.py", line 889, in _get_dataset_impl
    dataset.set_format(type="torch", columns=["input_ids", "attention_mask"])
  File "/root/.venv/lib/python3.12/site-packages/datasets/fingerprint.py", line 468, in wrapper
    out = func(dataset, *args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.venv/lib/python3.12/site-packages/datasets/arrow_dataset.py", line 2916, in set_format
    raise ValueError(
ValueError: Columns ['attention_mask'] not in the dataset. Current columns in the dataset: ['text', 'meta', 'input_ids']

Auto-generated by error_analysis pipeline. cc @lvkaokao