{
  "_name_or_path": "deepseek-vl2-deepseekmoe-tiny_add_speech_token_4096_nostrip",
  "architectures": [
    "DeepseekV2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_deepseek.DeepseekV2Config",
    "AutoModel": "modeling_deepseek.DeepseekV2Model",
    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
  },
  "aux_loss_alpha": 0.001,
  "bos_token_id": 0,
  "eos_token_id": 1,
  "ep_size": 1,
  "first_k_dense_replace": 1,
  "hidden_act": "silu",
  "hidden_size": 1280,
  "initializer_range": 0.02,
  "intermediate_size": 6848,
  "kv_lora_rank": null,
  "lm_head": true,
  "max_position_embeddings": 4096,
  "model_type": "deepseek_v2",
  "moe_intermediate_size": 896,
  "moe_layer_freq": 1,
  "n_group": 1,
  "n_routed_experts": 64,
  "n_shared_experts": 2,
  "norm_topk_prob": false,
  "num_attention_heads": 10,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 12,
  "num_key_value_heads": 10,
  "pretraining_tp": 1,
  "q_lora_rank": null,
  "qk_nope_head_dim": 0,
  "qk_rope_head_dim": 0,
  "rm_head": false,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "routed_scaling_factor": 1.0,
  "scoring_func": "softmax",
  "seq_aux": true,
  "tie_word_embeddings": false,
  "topk_group": 1,
  "topk_method": "greedy",
  "torch_dtype": "float32",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "use_mla": false,
  "v_head_dim": 0,
  "vocab_size": 132992
}