smash_config.json

{
    "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": "/ceph/hdd/staff/charpent/.cache/modelsvs_5k5xb",
        "batch_size": 1,
        "n_quantization_bits": 4,
        "tokenizer": "LlamaTokenizerFast(name_or_path='VMware/open-llama-7b-open-instruct', vocab_size=32000, model_max_length=2048, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>', 'pad_token': '<unk>'}, clean_up_tokenization_spaces=False),  added_tokens_decoder={\n\t0: AddedToken(\"<unk>\", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),\n\t1: AddedToken(\"<s>\", 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}",
        "model_config": "{'vocab_size': 32000, 'max_position_embeddings': 2048, 'hidden_size': 4096, 'intermediate_size': 11008, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 32, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 10000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, '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': False, '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': ['LlamaForCausalLM'], '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': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'VMware/open-llama-7b-open-instruct', 'transformers_version': '4.37.1', 'model_type': 'llama'}",
        "model_name": "VMware/open-llama-7b-open-instruct",
        "pruning_ratio": 0.0,
        "output_deviation": 0.005,
        "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"
    }
}