{
    "_name_or_path": "/covalent/.cache/models/tmp4d4ly8jc9ebsoso6",
    "architectures": [
        "DogeForCausalLM"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_doge.DogeConfig",
        "AutoModelForCausalLM": "JingzeShi/Doge-60M-Instruct--modeling_doge.DogeForCausalLM"
    },
    "bos_token_id": 1,
    "eos_token_id": 2,
    "expert_retrieval_size": 256,
    "hidden_act": "silu",
    "hidden_bias": false,
    "hidden_dropout": 0.0,
    "hidden_size": 512,
    "initializer_range": 0.02,
    "intermediate_size": 2048,
    "is_moe": false,
    "max_position_embeddings": 2048,
    "model_type": "doge",
    "num_attention_heads": 4,
    "num_cdmmoe_experts": 4096,
    "num_cdmmoe_experts_per_head": 8,
    "num_cdmmoe_heads": 4,
    "num_hidden_layers": 8,
    "pad_token_id": 0,
    "quantization_config": {
        "_load_in_4bit": false,
        "_load_in_8bit": true,
        "bnb_4bit_compute_dtype": "bfloat16",
        "bnb_4bit_quant_storage": "uint8",
        "bnb_4bit_quant_type": "fp4",
        "bnb_4bit_use_double_quant": false,
        "llm_int8_enable_fp32_cpu_offload": false,
        "llm_int8_has_fp16_weight": false,
        "llm_int8_skip_modules": [
            "lm_head"
        ],
        "llm_int8_threshold": 6.0,
        "load_in_4bit": false,
        "load_in_8bit": true,
        "quant_method": "bitsandbytes"
    },
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.46.2",
    "use_cache": true,
    "vocab_size": 32768,
    "api_key": null
}