{
    "_name_or_path": "/covalent/.cache/models/tmpisu30ysbnf2a0uqy",
    "architectures": [
        "DeepseekV3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_deepseek.DeepseekV3Config",
        "AutoModel": "tonyshark/deepdeek-v3-1b--modeling_deepseek.DeepseekV3Model",
        "AutoModelForCausalLM": "tonyshark/deepdeek-v3-1b--modeling_deepseek.DeepseekV3ForCausalLM"
    },
    "aux_loss_alpha": 0.001,
    "bos_token_id": 0,
    "eos_token_id": 1,
    "ep_size": 1,
    "first_k_dense_replace": 3,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 5376,
    "kv_lora_rank": 512,
    "max_position_embeddings": 163840,
    "model_type": "deepseek_v3",
    "moe_intermediate_size": 640,
    "moe_layer_freq": 1,
    "n_group": 8,
    "n_routed_experts": 32,
    "n_shared_experts": 1,
    "norm_topk_prob": true,
    "num_attention_heads": 8,
    "num_experts_per_tok": 4,
    "num_hidden_layers": 13,
    "num_key_value_heads": 8,
    "num_nextn_predict_layers": 1,
    "pretraining_tp": 1,
    "q_lora_rank": 1536,
    "qk_nope_head_dim": 128,
    "qk_rope_head_dim": 64,
    "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": {
        "beta_fast": 32,
        "beta_slow": 1,
        "factor": 40,
        "mscale": 1.0,
        "mscale_all_dim": 1.0,
        "original_max_position_embeddings": 4096,
        "type": "yarn"
    },
    "rope_theta": 10000,
    "routed_scaling_factor": 2.5,
    "scoring_func": "sigmoid",
    "seq_aux": true,
    "tie_word_embeddings": false,
    "topk_group": 4,
    "topk_method": "noaux_tc",
    "torch_dtype": "float16",
    "transformers_version": "4.46.2",
    "use_cache": true,
    "v_head_dim": 128,
    "vocab_size": 129280,
    "api_key": null
}