{
    "api_key": null,
    "verify_url": "http://johnrachwan.pythonanywhere.com",
    "smash_config": {
        "pruners": "None",
        "factorizers": "None",
        "quantizers": "['llm-int8']",
        "compilers": "None",
        "task": "text_text_generation",
        "device": "cuda",
        "cache_dir": "/efs/sommer/cache/wdzixvjn",
        "batch_size": 1,
        "tokenizer_name": "GPT2TokenizerFast(name_or_path='facebook/opt-125m', vocab_size=50265, model_max_length=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '</s>', 'eos_token': '</s>', 'unk_token': '</s>', 'pad_token': '<pad>'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={\n\t1: AddedToken(\"<pad>\", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),\n\t2: AddedToken(\"</s>\", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),\n}",
        "pruning_type": "structured-taylor",
        "sparsity_level": 0.5,
        "head_pruning_ratio": 0.5,
        "iterative_steps": 1,
        "sequence_length": 2048,
        "calibration_data_size": 10,
        "global_pruning": false,
        "ignore_embeddings": false,
        "prune_head_dims": false,
        "prune_num_heads": true,
        "ignored_layers": "[0, 1, 10, 11]",
        "pruning_ratio": 0.0,
        "model_configs": "{'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float16', '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': ['OPTForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': '</s>', 'bos_token_id': 2, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/opt-125m', 'transformers_version': '4.44.2', 'activation_dropout': 0.0, 'model_type': 'opt', 'vocab_size': 50272, 'max_position_embeddings': 2048, 'num_attention_heads': 12, 'word_embed_proj_dim': 768, 'ffn_dim': 3072, 'hidden_size': 768, 'num_hidden_layers': 12, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'layerdrop': 0.0, 'use_cache': True, 'do_layer_norm_before': True, 'enable_bias': True, 'layer_norm_elementwise_affine': True, '_remove_final_layer_norm': False}",
        "model_name": "facebook/opt-125m",
        "weight_quantization_bits": 8,
        "output_deviation": 0.0,
        "max_batch_size": 1,
        "qtype_weight": "torch.qint8",
        "qtype_activation": "torch.quint8",
        "qobserver": "<class 'torch.ao.quantization.observer.MinMaxObserver'>",
        "qscheme": "torch.per_tensor_symmetric",
        "qconfig": "x86",
        "group_size": 128,
        "damp_percent": 0.1,
        "save_load_fn": "bitsandbytes"
    }
}