| { | |
| "architectures": [ | |
| "DeepseekV32ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_deepseek_v32.DeepseekV32Config", | |
| "AutoModelForCausalLM": "modeling_deepseek_v32.DeepseekV32ForCausalLM" | |
| }, | |
| "dtype": "bfloat16", | |
| "ep_size": 1, | |
| "firts_k_dense_replace": 1, | |
| "head_dim": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 32, | |
| "index_head_dim": 4, | |
| "index_n_heads": 4, | |
| "index_topk": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 16, | |
| "kv_lora_rank": 2, | |
| "tie_word_embeddings": true, | |
| "max_position_embeddings": 163840, | |
| "mlp_layer_types": [ | |
| "dense", | |
| "sparse" | |
| ], | |
| "model_type": "deepseek_v32", | |
| "moe_intermediate_size": 4, | |
| "moe_layer_freq": 1, | |
| "n_group": 1, | |
| "n_routed_experts": 16, | |
| "n_shared_experts": 1, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 2, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 2, | |
| "num_nextn_predict_layers": 1, | |
| "q_lora_rank": 2, | |
| "qk_head_dim": 6, | |
| "qk_nope_head_dim": 4, | |
| "qk_rope_head_dim": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_interleave": true, | |
| "rope_scaling": { | |
| "beta_fast": 32.0, | |
| "beta_slow": 1.0, | |
| "factor": 40.0, | |
| "mscale": 1.0, | |
| "mscale_all_dim": 1.0, | |
| "original_max_position_embeddings": 4096, | |
| "rope_theta": 10000, | |
| "rope_type": "yarn", | |
| "type": "yarn" | |
| }, | |
| "rope_theta": 10000.0, | |
| "routed_scaling_factor": 2.5, | |
| "scoring_func": "sigmoid", | |
| "topk_group": 4, | |
| "topk_method": "noaux_tc", | |
| "transformers_version": "4.57.1", | |
| "use_cache": true, | |
| "v_head_dim": 2, | |
| "vocab_size": 129280 | |
| } | |