| { | |
| "mlp_bias": false, | |
| "attn_bias": false, | |
| "rotary_base": 10000, | |
| "rotary_scaling": { | |
| "beta_fast": 32, | |
| "beta_slow": 1, | |
| "factor": 40, | |
| "mscale": 1.0, | |
| "mscale_all_dim": 1.0, | |
| "original_max_position_embeddings": 4096, | |
| "type": "yarn" | |
| }, | |
| "residual_mlp": false, | |
| "disable_weight_only_quant_plugin": false, | |
| "moe": { | |
| "num_experts": 256, | |
| "shared_expert_intermediate_size": 2048, | |
| "top_k": 8, | |
| "normalization_mode": 3, | |
| "sparse_mixer_epsilon": 0.01, | |
| "tp_mode": 0, | |
| "topk_method": 2, | |
| "device_limited_n_group": 8, | |
| "device_limited_topk_group": 4, | |
| "device_limited_routed_scaling_factor": 2.5 | |
| }, | |
| "remove_duplicated_kv_heads": false, | |
| "fc_after_embed": false, | |
| "use_input_layernorm_in_first_layer": true, | |
| "use_last_layernorm": true, | |
| "layer_idx_offset": 0, | |
| "architecture": "DeepseekV2ForCausalLM", | |
| "dtype": "bfloat16", | |
| "vocab_size": 129280, | |
| "hidden_size": 7168, | |
| "num_hidden_layers": 61, | |
| "num_attention_heads": 128, | |
| "hidden_act": "swiglu", | |
| "logits_dtype": "float32", | |
| "norm_epsilon": 1e-06, | |
| "runtime_defaults": null, | |
| "position_embedding_type": "rope_gpt_neox", | |
| "num_key_value_heads": 128, | |
| "intermediate_size": 18432, | |
| "max_position_embeddings": 163840, | |
| "mapping": { | |
| "world_size": 4, | |
| "gpus_per_node": 8, | |
| "cp_size": 1, | |
| "tp_size": 4, | |
| "pp_size": 1, | |
| "moe_tp_size": 4, | |
| "moe_ep_size": 1 | |
| }, | |
| "quantization": { | |
| "quant_algo": "W4A16", | |
| "kv_cache_quant_algo": null, | |
| "group_size": 128, | |
| "smoothquant_val": 0.5, | |
| "clamp_val": null, | |
| "use_meta_recipe": false, | |
| "has_zero_point": false, | |
| "pre_quant_scale": false, | |
| "exclude_modules": null | |
| }, | |
| "use_parallel_embedding": false, | |
| "embedding_sharding_dim": 0, | |
| "head_size": 56, | |
| "qk_layernorm": false, | |
| "rotary_embedding_dim": 56, | |
| "moe_inter_size": 2048, | |
| "kv_lora_rank": 512, | |
| "q_lora_rank": 1536, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "v_head_dim": 128, | |
| "topk_method": "noaux_tc", | |
| "first_k_dense_replace": 3, | |
| "moe_layer_freq": 1, | |
| "coring_func": "sigmoid", | |
| "fp8_format": false | |
| } |