mlx-community

/

dbrx-instruct-4bit

like 48

Follow

MLX Community 2,426

I received the following traceback after an attempt to run configuration_dbrx.py after answering Y to the mlx_lm.convert's prompt for running the custom code

% python -m mlx_lm.convert --hf-path mlx-community/dbrx-instruct-4bit --mlx-path raw_models/mlx/dbrx
[..snip..]
Do you wish to run the custom code? [y/N] Y
Traceback (most recent call last):
[..snip..]
  File "/path/configuration_dbrx.py", line 233, in __init__
    self.attn_config = DbrxAttentionConfig(**attn_config)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/path/configuration_dbrx.py", line 48, in __init__
    raise ValueError(f'Found unknown {kwargs=}')
ValueError: Found unknown kwargs={'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': None, 'finetuning_task': None, 'id2label': {'0': 'LABEL_0', '1': 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': ''}