| { | |
| "architectures": [ | |
| "DeepseekV3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "aux_loss_alpha": 0.001, | |
| "bos_token_id": 0, | |
| "eos_token_id": 1, | |
| "ep_size": 1, | |
| "first_k_dense_replace": 62, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.006, | |
| "intermediate_size": 36864, | |
| "kv_lora_rank": 512, | |
| "max_position_embeddings": 2048, | |
| "model_type": "deepseek_v3", | |
| "moe_intermediate_size": 2048, | |
| "moe_layer_freq": 1, | |
| "n_group": 8, | |
| "n_routed_experts": null, | |
| "n_shared_experts": 1, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 64, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 61, | |
| "num_key_value_heads": 64, | |
| "num_nextn_predict_layers": 1, | |
| "pretraining_tp": 1, | |
| "q_lora_rank": 1024, | |
| "qk_head_dim": 192, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "rms_norm_eps": 1e-06, | |
| "rope_interleave": true, | |
| "rope_scaling": null, | |
| "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": "4.51.3", | |
| "use_cache": true, | |
| "v_head_dim": 128, | |
| "vocab_size": 129280 | |
| } | |