{
  "_name_or_path": "/nfs/scistore19/alistgrp/huggingface/hub/models--deepseek-ai--DeepSeek-R1/snapshots/f7361cd9ff99396dbf6bd644ad846015e59ed4fc",
  "architectures": [
    "DeepseekV3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
    "AutoModel": "modeling_deepseek.DeepseekV3Model",
    "AutoModelForCausalLM": "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": 7168,
  "initializer_range": 0.02,
  "intermediate_size": 18432,
  "kv_lora_rank": 512,
  "max_position_embeddings": 163840,
  "model_type": "deepseek_v3",
  "moe_intermediate_size": 2048,
  "moe_layer_freq": 1,
  "n_group": 8,
  "n_routed_experts": 256,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 128,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 61,
  "num_key_value_heads": 128,
  "num_nextn_predict_layers": 1,
  "pretraining_tp": 1,
  "q_lora_rank": 1536,
  "qk_nope_head_dim": 128,
  "qk_rope_head_dim": 64,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 128,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "ignore": [
      "lm_head",
      "re:.*self_attn.*",
      "re:.*shared_experts.*",
      "re:.*mlp\\.(gate|up|gate_up|down)_proj.*"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  },
  "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": "bfloat16",
  "transformers_version": "4.50.0.dev0",
  "use_cache": true,
  "v_head_dim": 128,
  "vocab_size": 129280
}