| { | |
| "architectures": [ | |
| "AfmoeForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_afmoe.AfmoeConfig", | |
| "AutoModel": "modeling_afmoe.AfmoeModel", | |
| "AutoModelForCausalLM": "modeling_afmoe.AfmoeForCausalLM" | |
| }, | |
| "dtype": "bfloat16", | |
| "global_attn_every_n_layers": 4, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "load_balance_coeff": 0.001, | |
| "max_position_embeddings": 131072, | |
| "model_type": "afmoe", | |
| "moe_intermediate_size": 1024, | |
| "mup_enabled": true, | |
| "n_group": 1, | |
| "num_attention_heads": 32, | |
| "num_dense_layers": 2, | |
| "num_expert_groups": 1, | |
| "num_experts": 128, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 4, | |
| "num_limited_groups": 1, | |
| "num_shared_experts": 1, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "format": "pack-quantized", | |
| "input_activations": null, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": 32, | |
| "num_bits": 4, | |
| "observer": "mse", | |
| "observer_kwargs": {}, | |
| "strategy": "group", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "pack-quantized", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| "model.layers.0.self_attn.q_proj", | |
| "model.layers.0.self_attn.k_proj", | |
| "model.layers.0.self_attn.v_proj", | |
| "model.layers.0.self_attn.o_proj", | |
| "model.layers.0.self_attn.gate_proj", | |
| "model.layers.0.mlp.gate_proj", | |
| "model.layers.0.mlp.up_proj", | |
| "model.layers.0.mlp.down_proj", | |
| "model.layers.1.self_attn.q_proj", | |
| "model.layers.1.self_attn.k_proj", | |
| "model.layers.1.self_attn.v_proj", | |
| "model.layers.1.self_attn.o_proj", | |
| "model.layers.1.self_attn.gate_proj", | |
| "model.layers.1.mlp.gate_proj", | |
| "model.layers.1.mlp.up_proj", | |
| "model.layers.1.mlp.down_proj", | |
| "model.layers.2.mlp.router.gate", | |
| "model.layers.2.mlp.shared_experts.gate_proj", | |
| "model.layers.2.mlp.shared_experts.up_proj", | |
| "model.layers.2.mlp.shared_experts.down_proj", | |
| "model.layers.3.mlp.router.gate", | |
| "model.layers.3.mlp.shared_experts.gate_proj", | |
| "model.layers.3.mlp.shared_experts.up_proj", | |
| "model.layers.3.mlp.shared_experts.down_proj", | |
| "model.layers.4.mlp.router.gate", | |
| "model.layers.4.mlp.shared_experts.gate_proj", | |
| "model.layers.4.mlp.shared_experts.up_proj", | |
| "model.layers.4.mlp.shared_experts.down_proj", | |
| "model.layers.5.mlp.router.gate", | |
| "model.layers.5.mlp.shared_experts.gate_proj", | |
| "model.layers.5.mlp.shared_experts.up_proj", | |
| "model.layers.5.mlp.shared_experts.down_proj", | |
| "model.layers.6.mlp.router.gate", | |
| "model.layers.6.mlp.shared_experts.gate_proj", | |
| "model.layers.6.mlp.shared_experts.up_proj", | |
| "model.layers.6.mlp.shared_experts.down_proj", | |
| "model.layers.7.mlp.router.gate", | |
| "model.layers.7.mlp.shared_experts.gate_proj", | |
| "model.layers.7.mlp.shared_experts.up_proj", | |
| "model.layers.7.mlp.shared_experts.down_proj", | |
| "model.layers.8.mlp.router.gate", | |
| "model.layers.8.mlp.shared_experts.gate_proj", | |
| "model.layers.8.mlp.shared_experts.up_proj", | |
| "model.layers.8.mlp.shared_experts.down_proj", | |
| "model.layers.9.mlp.router.gate", | |
| "model.layers.9.mlp.shared_experts.gate_proj", | |
| "model.layers.9.mlp.shared_experts.up_proj", | |
| "model.layers.9.mlp.shared_experts.down_proj", | |
| "model.layers.10.mlp.router.gate", | |
| "model.layers.10.mlp.shared_experts.gate_proj", | |
| "model.layers.10.mlp.shared_experts.up_proj", | |
| "model.layers.10.mlp.shared_experts.down_proj", | |
| "model.layers.11.mlp.router.gate", | |
| "model.layers.11.mlp.shared_experts.gate_proj", | |
| "model.layers.11.mlp.shared_experts.up_proj", | |
| "model.layers.11.mlp.shared_experts.down_proj", | |
| "model.layers.12.mlp.router.gate", | |
| "model.layers.12.mlp.shared_experts.gate_proj", | |
| "model.layers.12.mlp.shared_experts.up_proj", | |
| "model.layers.12.mlp.shared_experts.down_proj", | |
| "model.layers.13.mlp.router.gate", | |
| "model.layers.13.mlp.shared_experts.gate_proj", | |
| "model.layers.13.mlp.shared_experts.up_proj", | |
| "model.layers.13.mlp.shared_experts.down_proj", | |
| "model.layers.14.mlp.router.gate", | |
| "model.layers.14.mlp.shared_experts.gate_proj", | |
| "model.layers.14.mlp.shared_experts.up_proj", | |
| "model.layers.14.mlp.shared_experts.down_proj", | |
| "model.layers.15.mlp.router.gate", | |
| "model.layers.15.mlp.shared_experts.gate_proj", | |
| "model.layers.15.mlp.shared_experts.up_proj", | |
| "model.layers.15.mlp.shared_experts.down_proj", | |
| "model.layers.16.mlp.router.gate", | |
| "model.layers.16.mlp.shared_experts.gate_proj", | |
| "model.layers.16.mlp.shared_experts.up_proj", | |
| "model.layers.16.mlp.shared_experts.down_proj", | |
| "model.layers.17.mlp.router.gate", | |
| "model.layers.17.mlp.shared_experts.gate_proj", | |
| "model.layers.17.mlp.shared_experts.up_proj", | |
| "model.layers.17.mlp.shared_experts.down_proj", | |
| "model.layers.18.mlp.router.gate", | |
| "model.layers.18.mlp.shared_experts.gate_proj", | |
| "model.layers.18.mlp.shared_experts.up_proj", | |
| "model.layers.18.mlp.shared_experts.down_proj", | |
| "model.layers.19.mlp.router.gate", | |
| "model.layers.19.mlp.shared_experts.gate_proj", | |
| "model.layers.19.mlp.shared_experts.up_proj", | |
| "model.layers.19.mlp.shared_experts.down_proj", | |
| "model.layers.20.mlp.router.gate", | |
| "model.layers.20.mlp.shared_experts.gate_proj", | |
| "model.layers.20.mlp.shared_experts.up_proj", | |
| "model.layers.20.mlp.shared_experts.down_proj", | |
| "model.layers.21.mlp.router.gate", | |
| "model.layers.21.mlp.shared_experts.gate_proj", | |
| "model.layers.21.mlp.shared_experts.up_proj", | |
| "model.layers.21.mlp.shared_experts.down_proj", | |
| "model.layers.22.mlp.router.gate", | |
| "model.layers.22.mlp.shared_experts.gate_proj", | |
| "model.layers.22.mlp.shared_experts.up_proj", | |
| "model.layers.22.mlp.shared_experts.down_proj", | |
| "model.layers.23.mlp.router.gate", | |
| "model.layers.23.mlp.shared_experts.gate_proj", | |
| "model.layers.23.mlp.shared_experts.up_proj", | |
| "model.layers.23.mlp.shared_experts.down_proj", | |
| "model.layers.24.mlp.router.gate", | |
| "model.layers.24.mlp.shared_experts.gate_proj", | |
| "model.layers.24.mlp.shared_experts.up_proj", | |
| "model.layers.24.mlp.shared_experts.down_proj", | |
| "model.layers.25.mlp.router.gate", | |
| "model.layers.25.mlp.shared_experts.gate_proj", | |
| "model.layers.25.mlp.shared_experts.up_proj", | |
| "model.layers.25.mlp.shared_experts.down_proj", | |
| "model.layers.26.mlp.router.gate", | |
| "model.layers.26.mlp.shared_experts.gate_proj", | |
| "model.layers.26.mlp.shared_experts.up_proj", | |
| "model.layers.26.mlp.shared_experts.down_proj", | |
| "model.layers.27.mlp.router.gate", | |
| "model.layers.27.mlp.shared_experts.gate_proj", | |
| "model.layers.27.mlp.shared_experts.up_proj", | |
| "model.layers.27.mlp.shared_experts.down_proj", | |
| "model.layers.28.mlp.router.gate", | |
| "model.layers.28.mlp.shared_experts.gate_proj", | |
| "model.layers.28.mlp.shared_experts.up_proj", | |
| "model.layers.28.mlp.shared_experts.down_proj", | |
| "model.layers.29.mlp.router.gate", | |
| "model.layers.29.mlp.shared_experts.gate_proj", | |
| "model.layers.29.mlp.shared_experts.up_proj", | |
| "model.layers.29.mlp.shared_experts.down_proj", | |
| "model.layers.30.mlp.router.gate", | |
| "model.layers.30.mlp.shared_experts.gate_proj", | |
| "model.layers.30.mlp.shared_experts.up_proj", | |
| "model.layers.30.mlp.shared_experts.down_proj", | |
| "model.layers.31.mlp.router.gate", | |
| "model.layers.31.mlp.shared_experts.gate_proj", | |
| "model.layers.31.mlp.shared_experts.up_proj", | |
| "model.layers.31.mlp.shared_experts.down_proj", | |
| "lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed", | |
| "sparsity_config": {}, | |
| "transform_config": {}, | |
| "version": "0.12.3.a20251114" | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "route_norm": true, | |
| "route_scale": 2.826, | |
| "score_func": "sigmoid", | |
| "sliding_window": 2048, | |
| "tie_word_embeddings": false, | |
| "topk_group": 1, | |
| "transformers_version": "4.57.3", | |
| "use_cache": true, | |
| "use_grouped_mm": true, | |
| "vocab_size": 200192 | |
| } | |