{
    "add_cross_attention": false,
    "architectures": [
        "DbrxForCausalLM"
    ],
    "attn_config": {
        "return_dict": true,
        "output_hidden_states": false,
        "output_attentions": false,
        "torchscript": false,
        "torch_dtype": null,
        "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": null,
        "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": null,
        "num_return_sequences": 1,
        "output_scores": false,
        "return_dict_in_generate": false,
        "forced_bos_token_id": null,
        "forced_eos_token_id": null,
        "remove_invalid_values": false,
        "exponential_decay_length_penalty": null,
        "suppress_tokens": null,
        "begin_suppress_tokens": null,
        "architectures": null,
        "finetuning_task": null,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "tokenizer_class": null,
        "prefix": null,
        "bos_token_id": null,
        "pad_token_id": null,
        "eos_token_id": null,
        "sep_token_id": null,
        "decoder_start_token_id": null,
        "task_specific_params": null,
        "problem_type": null,
        "_name_or_path": "",
        "model_type": "",
        "attn_pdrop": 0,
        "clip_qkv": 8,
        "kv_n_heads": 8,
        "rope_theta": 500000
    },
    "auto_map": {
        "AutoConfig": "configuration_dbrx.DbrxConfig",
        "AutoModelForCausalLM": "modeling_dbrx.DbrxForCausalLM"
    },
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "d_model": 6144,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "emb_pdrop": 0.0,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "ffn_config": {
        "return_dict": true,
        "output_hidden_states": false,
        "output_attentions": false,
        "torchscript": false,
        "torch_dtype": null,
        "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": null,
        "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": null,
        "num_return_sequences": 1,
        "output_scores": false,
        "return_dict_in_generate": false,
        "forced_bos_token_id": null,
        "forced_eos_token_id": null,
        "remove_invalid_values": false,
        "exponential_decay_length_penalty": null,
        "suppress_tokens": null,
        "begin_suppress_tokens": null,
        "architectures": null,
        "finetuning_task": null,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "tokenizer_class": null,
        "prefix": null,
        "bos_token_id": null,
        "pad_token_id": null,
        "eos_token_id": null,
        "sep_token_id": null,
        "decoder_start_token_id": null,
        "task_specific_params": null,
        "problem_type": null,
        "_name_or_path": "",
        "ffn_act_fn": {
            "name": "silu"
        },
        "ffn_hidden_size": 10752,
        "moe_num_experts": 16,
        "moe_top_k": 4,
        "moe_jitter_eps": 0,
        "moe_loss_weight": 0.05,
        "moe_normalize_expert_weights": 1,
        "uniform_expert_assignment": false,
        "model_type": ""
    },
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_seq_len": 32768,
    "min_length": 0,
    "model_type": "dbrx",
    "n_heads": 48,
    "n_layers": 40,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_router_logits": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "quantization": {
        "group_size": 64,
        "bits": 4
    },
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "resid_pdrop": 0.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "router_aux_loss_coef": 0.05,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "bfloat16",
    "torchscript": false,
    "transformers_version": "4.39.2",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 100352
}