| { |
| "architectures": ["OpenPanguV2ForCausalLM"], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_openpangu_v2.OpenPanguV2Config" |
| }, |
| "_attn_implementation":"eager", |
| "block_post_layernorm_idx": [0, 4, 9, 14, 19, 24, 29, 34, 39], |
| "bos_token_id": 148899, |
| "dsa_layers": [0, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, 36, 39, 42, 45], |
| "dtype": "bfloat16", |
| "eos_token_id": 148902, |
| "first_k_dense_replace": 2, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "index_head_dim": 128, |
| "index_n_heads": 24, |
| "index_topk": 2048, |
| "intermediate_size": 9216, |
| "kv_lora_rank": 512, |
| "max_position_embeddings": 524288, |
| "mhc_num_stream": 4, |
| "mhc_recur_norm": 20, |
| "mhc_use_gamma": true, |
| "model_type": "openpangu_v2", |
| "moe_intermediate_size": 1024, |
| "n_routed_experts": 256, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 48, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 46, |
| "num_nextn_predict_layers": 3, |
| "pad_token_id": 148902, |
| "param_sink_number": 128, |
| "q_lora_rank": 1024, |
| "qk_nope_head_dim": 128, |
| "qk_rope_head_dim": 64, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 6400000, |
| "rope_interleave": false, |
| "router_enable_expert_bias": true, |
| "routed_scaling_factor": 2.5, |
| "router_sliding_window": 3, |
| "sandwich_norm": true, |
| "sliding_window": 512, |
| "sliding_window_list": [512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 2048, 2048, 2048], |
| "swa_layers": [1, 2, 4, 5, 7, 8, 10, 11, 13, 14, 16, 17, 19, 20, 22, 23, 25, 26, 28, 29, 31, 32, 34, 35, 37, 38, 40, 41, 43, 44, 46, 47, 48], |
| "tie_word_embeddings": false, |
| "transformers_version": "5.0.0", |
| "use_cache": true, |
| "use_mhc": true, |
| "use_mome": true, |
| "v_head_dim": 128, |
| "vocab_size": 151552, |
| "quantization_config": { |
| "quant_method": "compressed-tensors", |
| "quantize": "w8a8_dynamic", |
| "format": "int-quantized", |
| "quantization_status": "compressed", |
| "config_groups": { |
| "group_0": { |
| "format": "int-quantized", |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "type": "int", |
| "num_bits": 8, |
| "symmetric": true, |
| "strategy": "channel", |
| "dynamic": false, |
| "observer": "minmax", |
| "actorder": null, |
| "group_size": null, |
| "block_structure": null, |
| "observer_kwargs": {} |
| }, |
| "input_activations": { |
| "type": "int", |
| "num_bits": 8, |
| "symmetric": true, |
| "strategy": "token", |
| "dynamic": true, |
| "actorder": null, |
| "group_size": null, |
| "block_structure": null, |
| "observer": null, |
| "observer_kwargs": {} |
| }, |
| "output_activations": null |
| } |
| }, |
| "ignore": [ |
| "lm_head", |
| "model.embed_tokens", |
| "model.layers.0.attn_mhc_module.phi", |
| "model.layers.0.mlp_mhc_module.phi", |
| "model.layers.0.self_attn.indexer.weights_proj", |
| "model.layers.0.self_attn.indexer.wk", |
| "model.layers.0.self_attn.indexer.wq_b", |
| "model.layers.0.self_attn.kv_a_proj_with_mqa", |
| "model.layers.0.self_attn.kv_b_proj", |
| "model.layers.0.self_attn.q_a_proj", |
| "model.layers.1.attn_mhc_module.phi", |
| "model.layers.1.mlp_mhc_module.phi", |
| "model.layers.1.self_attn.kv_a_proj_with_mqa", |
| "model.layers.1.self_attn.kv_b_proj", |
| "model.layers.1.self_attn.q_a_proj", |
| "model.layers.10.attn_mhc_module.phi", |
| "model.layers.10.mlp.gate", |
| "model.layers.10.mlp.shared_experts.down_proj", |
| "model.layers.10.mlp.shared_experts.gate_proj", |
| "model.layers.10.mlp.shared_experts.up_proj", |
| "model.layers.10.mlp_mhc_module.phi", |
| "model.layers.10.self_attn.kv_a_proj_with_mqa", |
| "model.layers.10.self_attn.kv_b_proj", |
| "model.layers.10.self_attn.q_a_proj", |
| "model.layers.11.attn_mhc_module.phi", |
| "model.layers.11.mlp.gate", |
| "model.layers.11.mlp.shared_experts.down_proj", |
| "model.layers.11.mlp.shared_experts.gate_proj", |
| "model.layers.11.mlp.shared_experts.up_proj", |
| "model.layers.11.mlp_mhc_module.phi", |
| "model.layers.11.self_attn.kv_a_proj_with_mqa", |
| "model.layers.11.self_attn.kv_b_proj", |
| "model.layers.11.self_attn.q_a_proj", |
| "model.layers.12.attn_mhc_module.phi", |
| "model.layers.12.mlp.gate", |
| "model.layers.12.mlp.shared_experts.down_proj", |
| "model.layers.12.mlp.shared_experts.gate_proj", |
| "model.layers.12.mlp.shared_experts.up_proj", |
| "model.layers.12.mlp_mhc_module.phi", |
| "model.layers.12.self_attn.indexer.weights_proj", |
| "model.layers.12.self_attn.indexer.wk", |
| "model.layers.12.self_attn.indexer.wq_b", |
| "model.layers.12.self_attn.kv_a_proj_with_mqa", |
| "model.layers.12.self_attn.kv_b_proj", |
| "model.layers.12.self_attn.q_a_proj", |
| "model.layers.13.attn_mhc_module.phi", |
| "model.layers.13.mlp.gate", |
| "model.layers.13.mlp.shared_experts.down_proj", |
| "model.layers.13.mlp.shared_experts.gate_proj", |
| "model.layers.13.mlp.shared_experts.up_proj", |
| "model.layers.13.mlp_mhc_module.phi", |
| "model.layers.13.self_attn.kv_a_proj_with_mqa", |
| "model.layers.13.self_attn.kv_b_proj", |
| "model.layers.13.self_attn.q_a_proj", |
| "model.layers.14.attn_mhc_module.phi", |
| "model.layers.14.mlp.gate", |
| "model.layers.14.mlp.shared_experts.down_proj", |
| "model.layers.14.mlp.shared_experts.gate_proj", |
| "model.layers.14.mlp.shared_experts.up_proj", |
| "model.layers.14.mlp_mhc_module.phi", |
| "model.layers.14.self_attn.kv_a_proj_with_mqa", |
| "model.layers.14.self_attn.kv_b_proj", |
| "model.layers.14.self_attn.q_a_proj", |
| "model.layers.15.attn_mhc_module.phi", |
| "model.layers.15.mlp.gate", |
| "model.layers.15.mlp.shared_experts.down_proj", |
| "model.layers.15.mlp.shared_experts.gate_proj", |
| "model.layers.15.mlp.shared_experts.up_proj", |
| "model.layers.15.mlp_mhc_module.phi", |
| "model.layers.15.self_attn.indexer.weights_proj", |
| "model.layers.15.self_attn.indexer.wk", |
| "model.layers.15.self_attn.indexer.wq_b", |
| "model.layers.15.self_attn.kv_a_proj_with_mqa", |
| "model.layers.15.self_attn.kv_b_proj", |
| "model.layers.15.self_attn.q_a_proj", |
| "model.layers.16.attn_mhc_module.phi", |
| "model.layers.16.mlp.gate", |
| "model.layers.16.mlp.shared_experts.down_proj", |
| "model.layers.16.mlp.shared_experts.gate_proj", |
| "model.layers.16.mlp.shared_experts.up_proj", |
| "model.layers.16.mlp_mhc_module.phi", |
| "model.layers.16.self_attn.kv_a_proj_with_mqa", |
| "model.layers.16.self_attn.kv_b_proj", |
| "model.layers.16.self_attn.q_a_proj", |
| "model.layers.17.attn_mhc_module.phi", |
| "model.layers.17.mlp.gate", |
| "model.layers.17.mlp.shared_experts.down_proj", |
| "model.layers.17.mlp.shared_experts.gate_proj", |
| "model.layers.17.mlp.shared_experts.up_proj", |
| "model.layers.17.mlp_mhc_module.phi", |
| "model.layers.17.self_attn.kv_a_proj_with_mqa", |
| "model.layers.17.self_attn.kv_b_proj", |
| "model.layers.17.self_attn.q_a_proj", |
| "model.layers.18.attn_mhc_module.phi", |
| "model.layers.18.mlp.gate", |
| "model.layers.18.mlp.shared_experts.down_proj", |
| "model.layers.18.mlp.shared_experts.gate_proj", |
| "model.layers.18.mlp.shared_experts.up_proj", |
| "model.layers.18.mlp_mhc_module.phi", |
| "model.layers.18.self_attn.indexer.weights_proj", |
| "model.layers.18.self_attn.indexer.wk", |
| "model.layers.18.self_attn.indexer.wq_b", |
| "model.layers.18.self_attn.kv_a_proj_with_mqa", |
| "model.layers.18.self_attn.kv_b_proj", |
| "model.layers.18.self_attn.q_a_proj", |
| "model.layers.19.attn_mhc_module.phi", |
| "model.layers.19.mlp.gate", |
| "model.layers.19.mlp.shared_experts.down_proj", |
| "model.layers.19.mlp.shared_experts.gate_proj", |
| "model.layers.19.mlp.shared_experts.up_proj", |
| "model.layers.19.mlp_mhc_module.phi", |
| "model.layers.19.self_attn.kv_a_proj_with_mqa", |
| "model.layers.19.self_attn.kv_b_proj", |
| "model.layers.19.self_attn.q_a_proj", |
| "model.layers.2.attn_mhc_module.phi", |
| "model.layers.2.mlp.gate", |
| "model.layers.2.mlp.shared_experts.down_proj", |
| "model.layers.2.mlp.shared_experts.gate_proj", |
| "model.layers.2.mlp.shared_experts.up_proj", |
| "model.layers.2.mlp_mhc_module.phi", |
| "model.layers.2.self_attn.kv_a_proj_with_mqa", |
| "model.layers.2.self_attn.kv_b_proj", |
| "model.layers.2.self_attn.q_a_proj", |
| "model.layers.20.attn_mhc_module.phi", |
| "model.layers.20.mlp.gate", |
| "model.layers.20.mlp.shared_experts.down_proj", |
| "model.layers.20.mlp.shared_experts.gate_proj", |
| "model.layers.20.mlp.shared_experts.up_proj", |
| "model.layers.20.mlp_mhc_module.phi", |
| "model.layers.20.self_attn.kv_a_proj_with_mqa", |
| "model.layers.20.self_attn.kv_b_proj", |
| "model.layers.20.self_attn.q_a_proj", |
| "model.layers.21.attn_mhc_module.phi", |
| "model.layers.21.mlp.gate", |
| "model.layers.21.mlp.shared_experts.down_proj", |
| "model.layers.21.mlp.shared_experts.gate_proj", |
| "model.layers.21.mlp.shared_experts.up_proj", |
| "model.layers.21.mlp_mhc_module.phi", |
| "model.layers.21.self_attn.indexer.weights_proj", |
| "model.layers.21.self_attn.indexer.wk", |
| "model.layers.21.self_attn.indexer.wq_b", |
| "model.layers.21.self_attn.kv_a_proj_with_mqa", |
| "model.layers.21.self_attn.kv_b_proj", |
| "model.layers.21.self_attn.q_a_proj", |
| "model.layers.22.attn_mhc_module.phi", |
| "model.layers.22.mlp.gate", |
| "model.layers.22.mlp.shared_experts.down_proj", |
| "model.layers.22.mlp.shared_experts.gate_proj", |
| "model.layers.22.mlp.shared_experts.up_proj", |
| "model.layers.22.mlp_mhc_module.phi", |
| "model.layers.22.self_attn.kv_a_proj_with_mqa", |
| "model.layers.22.self_attn.kv_b_proj", |
| "model.layers.22.self_attn.q_a_proj", |
| "model.layers.23.attn_mhc_module.phi", |
| "model.layers.23.mlp.gate", |
| "model.layers.23.mlp.shared_experts.down_proj", |
| "model.layers.23.mlp.shared_experts.gate_proj", |
| "model.layers.23.mlp.shared_experts.up_proj", |
| "model.layers.23.mlp_mhc_module.phi", |
| "model.layers.23.self_attn.kv_a_proj_with_mqa", |
| "model.layers.23.self_attn.kv_b_proj", |
| "model.layers.23.self_attn.q_a_proj", |
| "model.layers.24.attn_mhc_module.phi", |
| "model.layers.24.mlp.gate", |
| "model.layers.24.mlp.shared_experts.down_proj", |
| "model.layers.24.mlp.shared_experts.gate_proj", |
| "model.layers.24.mlp.shared_experts.up_proj", |
| "model.layers.24.mlp_mhc_module.phi", |
| "model.layers.24.self_attn.indexer.weights_proj", |
| "model.layers.24.self_attn.indexer.wk", |
| "model.layers.24.self_attn.indexer.wq_b", |
| "model.layers.24.self_attn.kv_a_proj_with_mqa", |
| "model.layers.24.self_attn.kv_b_proj", |
| "model.layers.24.self_attn.q_a_proj", |
| "model.layers.25.attn_mhc_module.phi", |
| "model.layers.25.mlp.gate", |
| "model.layers.25.mlp.shared_experts.down_proj", |
| "model.layers.25.mlp.shared_experts.gate_proj", |
| "model.layers.25.mlp.shared_experts.up_proj", |
| "model.layers.25.mlp_mhc_module.phi", |
| "model.layers.25.self_attn.kv_a_proj_with_mqa", |
| "model.layers.25.self_attn.kv_b_proj", |
| "model.layers.25.self_attn.q_a_proj", |
| "model.layers.26.attn_mhc_module.phi", |
| "model.layers.26.mlp.gate", |
| "model.layers.26.mlp.shared_experts.down_proj", |
| "model.layers.26.mlp.shared_experts.gate_proj", |
| "model.layers.26.mlp.shared_experts.up_proj", |
| "model.layers.26.mlp_mhc_module.phi", |
| "model.layers.26.self_attn.kv_a_proj_with_mqa", |
| "model.layers.26.self_attn.kv_b_proj", |
| "model.layers.26.self_attn.q_a_proj", |
| "model.layers.27.attn_mhc_module.phi", |
| "model.layers.27.mlp.gate", |
| "model.layers.27.mlp.shared_experts.down_proj", |
| "model.layers.27.mlp.shared_experts.gate_proj", |
| "model.layers.27.mlp.shared_experts.up_proj", |
| "model.layers.27.mlp_mhc_module.phi", |
| "model.layers.27.self_attn.indexer.weights_proj", |
| "model.layers.27.self_attn.indexer.wk", |
| "model.layers.27.self_attn.indexer.wq_b", |
| "model.layers.27.self_attn.kv_a_proj_with_mqa", |
| "model.layers.27.self_attn.kv_b_proj", |
| "model.layers.27.self_attn.q_a_proj", |
| "model.layers.28.attn_mhc_module.phi", |
| "model.layers.28.mlp.gate", |
| "model.layers.28.mlp.shared_experts.down_proj", |
| "model.layers.28.mlp.shared_experts.gate_proj", |
| "model.layers.28.mlp.shared_experts.up_proj", |
| "model.layers.28.mlp_mhc_module.phi", |
| "model.layers.28.self_attn.kv_a_proj_with_mqa", |
| "model.layers.28.self_attn.kv_b_proj", |
| "model.layers.28.self_attn.q_a_proj", |
| "model.layers.29.attn_mhc_module.phi", |
| "model.layers.29.mlp.gate", |
| "model.layers.29.mlp.shared_experts.down_proj", |
| "model.layers.29.mlp.shared_experts.gate_proj", |
| "model.layers.29.mlp.shared_experts.up_proj", |
| "model.layers.29.mlp_mhc_module.phi", |
| "model.layers.29.self_attn.kv_a_proj_with_mqa", |
| "model.layers.29.self_attn.kv_b_proj", |
| "model.layers.29.self_attn.q_a_proj", |
| "model.layers.3.attn_mhc_module.phi", |
| "model.layers.3.mlp.gate", |
| "model.layers.3.mlp.shared_experts.down_proj", |
| "model.layers.3.mlp.shared_experts.gate_proj", |
| "model.layers.3.mlp.shared_experts.up_proj", |
| "model.layers.3.mlp_mhc_module.phi", |
| "model.layers.3.self_attn.indexer.weights_proj", |
| "model.layers.3.self_attn.indexer.wk", |
| "model.layers.3.self_attn.indexer.wq_b", |
| "model.layers.3.self_attn.kv_a_proj_with_mqa", |
| "model.layers.3.self_attn.kv_b_proj", |
| "model.layers.3.self_attn.q_a_proj", |
| "model.layers.30.attn_mhc_module.phi", |
| "model.layers.30.mlp.gate", |
| "model.layers.30.mlp.shared_experts.down_proj", |
| "model.layers.30.mlp.shared_experts.gate_proj", |
| "model.layers.30.mlp.shared_experts.up_proj", |
| "model.layers.30.mlp_mhc_module.phi", |
| "model.layers.30.self_attn.indexer.weights_proj", |
| "model.layers.30.self_attn.indexer.wk", |
| "model.layers.30.self_attn.indexer.wq_b", |
| "model.layers.30.self_attn.kv_a_proj_with_mqa", |
| "model.layers.30.self_attn.kv_b_proj", |
| "model.layers.30.self_attn.q_a_proj", |
| "model.layers.31.attn_mhc_module.phi", |
| "model.layers.31.mlp.gate", |
| "model.layers.31.mlp.shared_experts.down_proj", |
| "model.layers.31.mlp.shared_experts.gate_proj", |
| "model.layers.31.mlp.shared_experts.up_proj", |
| "model.layers.31.mlp_mhc_module.phi", |
| "model.layers.31.self_attn.kv_a_proj_with_mqa", |
| "model.layers.31.self_attn.kv_b_proj", |
| "model.layers.31.self_attn.q_a_proj", |
| "model.layers.32.attn_mhc_module.phi", |
| "model.layers.32.mlp.gate", |
| "model.layers.32.mlp.shared_experts.down_proj", |
| "model.layers.32.mlp.shared_experts.gate_proj", |
| "model.layers.32.mlp.shared_experts.up_proj", |
| "model.layers.32.mlp_mhc_module.phi", |
| "model.layers.32.self_attn.kv_a_proj_with_mqa", |
| "model.layers.32.self_attn.kv_b_proj", |
| "model.layers.32.self_attn.q_a_proj", |
| "model.layers.33.attn_mhc_module.phi", |
| "model.layers.33.mlp.gate", |
| "model.layers.33.mlp.shared_experts.down_proj", |
| "model.layers.33.mlp.shared_experts.gate_proj", |
| "model.layers.33.mlp.shared_experts.up_proj", |
| "model.layers.33.mlp_mhc_module.phi", |
| "model.layers.33.self_attn.indexer.weights_proj", |
| "model.layers.33.self_attn.indexer.wk", |
| "model.layers.33.self_attn.indexer.wq_b", |
| "model.layers.33.self_attn.kv_a_proj_with_mqa", |
| "model.layers.33.self_attn.kv_b_proj", |
| "model.layers.33.self_attn.q_a_proj", |
| "model.layers.34.attn_mhc_module.phi", |
| "model.layers.34.mlp.gate", |
| "model.layers.34.mlp.shared_experts.down_proj", |
| "model.layers.34.mlp.shared_experts.gate_proj", |
| "model.layers.34.mlp.shared_experts.up_proj", |
| "model.layers.34.mlp_mhc_module.phi", |
| "model.layers.34.self_attn.kv_a_proj_with_mqa", |
| "model.layers.34.self_attn.kv_b_proj", |
| "model.layers.34.self_attn.q_a_proj", |
| "model.layers.35.attn_mhc_module.phi", |
| "model.layers.35.mlp.gate", |
| "model.layers.35.mlp.shared_experts.down_proj", |
| "model.layers.35.mlp.shared_experts.gate_proj", |
| "model.layers.35.mlp.shared_experts.up_proj", |
| "model.layers.35.mlp_mhc_module.phi", |
| "model.layers.35.self_attn.kv_a_proj_with_mqa", |
| "model.layers.35.self_attn.kv_b_proj", |
| "model.layers.35.self_attn.q_a_proj", |
| "model.layers.36.attn_mhc_module.phi", |
| "model.layers.36.mlp.gate", |
| "model.layers.36.mlp.shared_experts.down_proj", |
| "model.layers.36.mlp.shared_experts.gate_proj", |
| "model.layers.36.mlp.shared_experts.up_proj", |
| "model.layers.36.mlp_mhc_module.phi", |
| "model.layers.36.self_attn.indexer.weights_proj", |
| "model.layers.36.self_attn.indexer.wk", |
| "model.layers.36.self_attn.indexer.wq_b", |
| "model.layers.36.self_attn.kv_a_proj_with_mqa", |
| "model.layers.36.self_attn.kv_b_proj", |
| "model.layers.36.self_attn.q_a_proj", |
| "model.layers.37.attn_mhc_module.phi", |
| "model.layers.37.mlp.gate", |
| "model.layers.37.mlp.shared_experts.down_proj", |
| "model.layers.37.mlp.shared_experts.gate_proj", |
| "model.layers.37.mlp.shared_experts.up_proj", |
| "model.layers.37.mlp_mhc_module.phi", |
| "model.layers.37.self_attn.kv_a_proj_with_mqa", |
| "model.layers.37.self_attn.kv_b_proj", |
| "model.layers.37.self_attn.q_a_proj", |
| "model.layers.38.attn_mhc_module.phi", |
| "model.layers.38.mlp.gate", |
| "model.layers.38.mlp.shared_experts.down_proj", |
| "model.layers.38.mlp.shared_experts.gate_proj", |
| "model.layers.38.mlp.shared_experts.up_proj", |
| "model.layers.38.mlp_mhc_module.phi", |
| "model.layers.38.self_attn.kv_a_proj_with_mqa", |
| "model.layers.38.self_attn.kv_b_proj", |
| "model.layers.38.self_attn.q_a_proj", |
| "model.layers.39.attn_mhc_module.phi", |
| "model.layers.39.mlp.gate", |
| "model.layers.39.mlp.shared_experts.down_proj", |
| "model.layers.39.mlp.shared_experts.gate_proj", |
| "model.layers.39.mlp.shared_experts.up_proj", |
| "model.layers.39.mlp_mhc_module.phi", |
| "model.layers.39.self_attn.indexer.weights_proj", |
| "model.layers.39.self_attn.indexer.wk", |
| "model.layers.39.self_attn.indexer.wq_b", |
| "model.layers.39.self_attn.kv_a_proj_with_mqa", |
| "model.layers.39.self_attn.kv_b_proj", |
| "model.layers.39.self_attn.q_a_proj", |
| "model.layers.4.attn_mhc_module.phi", |
| "model.layers.4.mlp.gate", |
| "model.layers.4.mlp.shared_experts.down_proj", |
| "model.layers.4.mlp.shared_experts.gate_proj", |
| "model.layers.4.mlp.shared_experts.up_proj", |
| "model.layers.4.mlp_mhc_module.phi", |
| "model.layers.4.self_attn.kv_a_proj_with_mqa", |
| "model.layers.4.self_attn.kv_b_proj", |
| "model.layers.4.self_attn.q_a_proj", |
| "model.layers.40.attn_mhc_module.phi", |
| "model.layers.40.mlp.gate", |
| "model.layers.40.mlp.shared_experts.down_proj", |
| "model.layers.40.mlp.shared_experts.gate_proj", |
| "model.layers.40.mlp.shared_experts.up_proj", |
| "model.layers.40.mlp_mhc_module.phi", |
| "model.layers.40.self_attn.kv_a_proj_with_mqa", |
| "model.layers.40.self_attn.kv_b_proj", |
| "model.layers.40.self_attn.q_a_proj", |
| "model.layers.41.attn_mhc_module.phi", |
| "model.layers.41.mlp.gate", |
| "model.layers.41.mlp.shared_experts.down_proj", |
| "model.layers.41.mlp.shared_experts.gate_proj", |
| "model.layers.41.mlp.shared_experts.up_proj", |
| "model.layers.41.mlp_mhc_module.phi", |
| "model.layers.41.self_attn.kv_a_proj_with_mqa", |
| "model.layers.41.self_attn.kv_b_proj", |
| "model.layers.41.self_attn.q_a_proj", |
| "model.layers.42.attn_mhc_module.phi", |
| "model.layers.42.mlp.gate", |
| "model.layers.42.mlp.shared_experts.down_proj", |
| "model.layers.42.mlp.shared_experts.gate_proj", |
| "model.layers.42.mlp.shared_experts.up_proj", |
| "model.layers.42.mlp_mhc_module.phi", |
| "model.layers.42.self_attn.indexer.weights_proj", |
| "model.layers.42.self_attn.indexer.wk", |
| "model.layers.42.self_attn.indexer.wq_b", |
| "model.layers.42.self_attn.kv_a_proj_with_mqa", |
| "model.layers.42.self_attn.kv_b_proj", |
| "model.layers.42.self_attn.q_a_proj", |
| "model.layers.43.attn_mhc_module.phi", |
| "model.layers.43.mlp.gate", |
| "model.layers.43.mlp.shared_experts.down_proj", |
| "model.layers.43.mlp.shared_experts.gate_proj", |
| "model.layers.43.mlp.shared_experts.up_proj", |
| "model.layers.43.mlp_mhc_module.phi", |
| "model.layers.43.self_attn.kv_a_proj_with_mqa", |
| "model.layers.43.self_attn.kv_b_proj", |
| "model.layers.43.self_attn.q_a_proj", |
| "model.layers.44.attn_mhc_module.phi", |
| "model.layers.44.mlp.gate", |
| "model.layers.44.mlp.shared_experts.down_proj", |
| "model.layers.44.mlp.shared_experts.gate_proj", |
| "model.layers.44.mlp.shared_experts.up_proj", |
| "model.layers.44.mlp_mhc_module.phi", |
| "model.layers.44.self_attn.kv_a_proj_with_mqa", |
| "model.layers.44.self_attn.kv_b_proj", |
| "model.layers.44.self_attn.q_a_proj", |
| "model.layers.45.attn_mhc_module.phi", |
| "model.layers.45.mlp.gate", |
| "model.layers.45.mlp.shared_experts.down_proj", |
| "model.layers.45.mlp.shared_experts.gate_proj", |
| "model.layers.45.mlp.shared_experts.up_proj", |
| "model.layers.45.mlp_mhc_module.phi", |
| "model.layers.45.self_attn.indexer.weights_proj", |
| "model.layers.45.self_attn.indexer.wk", |
| "model.layers.45.self_attn.indexer.wq_b", |
| "model.layers.45.self_attn.kv_a_proj_with_mqa", |
| "model.layers.45.self_attn.kv_b_proj", |
| "model.layers.45.self_attn.q_a_proj", |
| "model.layers.46.embed_tokens", |
| "model.layers.46.mlp.gate", |
| "model.layers.46.mlp.shared_experts.down_proj", |
| "model.layers.46.mlp.shared_experts.gate_proj", |
| "model.layers.46.mlp.shared_experts.up_proj", |
| "model.layers.46.self_attn.kv_a_proj_with_mqa", |
| "model.layers.46.self_attn.kv_b_proj", |
| "model.layers.46.self_attn.q_a_proj", |
| "model.layers.46.shared_head.head", |
| "model.layers.47.embed_tokens", |
| "model.layers.47.mlp.gate", |
| "model.layers.47.mlp.shared_experts.down_proj", |
| "model.layers.47.mlp.shared_experts.gate_proj", |
| "model.layers.47.mlp.shared_experts.up_proj", |
| "model.layers.47.self_attn.kv_a_proj_with_mqa", |
| "model.layers.47.self_attn.kv_b_proj", |
| "model.layers.47.self_attn.q_a_proj", |
| "model.layers.47.shared_head.head", |
| "model.layers.48.embed_tokens", |
| "model.layers.48.mlp.gate", |
| "model.layers.48.mlp.shared_experts.down_proj", |
| "model.layers.48.mlp.shared_experts.gate_proj", |
| "model.layers.48.mlp.shared_experts.up_proj", |
| "model.layers.48.self_attn.kv_a_proj_with_mqa", |
| "model.layers.48.self_attn.kv_b_proj", |
| "model.layers.48.self_attn.q_a_proj", |
| "model.layers.48.shared_head.head", |
| "model.layers.5.attn_mhc_module.phi", |
| "model.layers.5.mlp.gate", |
| "model.layers.5.mlp.shared_experts.down_proj", |
| "model.layers.5.mlp.shared_experts.gate_proj", |
| "model.layers.5.mlp.shared_experts.up_proj", |
| "model.layers.5.mlp_mhc_module.phi", |
| "model.layers.5.self_attn.kv_a_proj_with_mqa", |
| "model.layers.5.self_attn.kv_b_proj", |
| "model.layers.5.self_attn.q_a_proj", |
| "model.layers.6.attn_mhc_module.phi", |
| "model.layers.6.mlp.gate", |
| "model.layers.6.mlp.shared_experts.down_proj", |
| "model.layers.6.mlp.shared_experts.gate_proj", |
| "model.layers.6.mlp.shared_experts.up_proj", |
| "model.layers.6.mlp_mhc_module.phi", |
| "model.layers.6.self_attn.indexer.weights_proj", |
| "model.layers.6.self_attn.indexer.wk", |
| "model.layers.6.self_attn.indexer.wq_b", |
| "model.layers.6.self_attn.kv_a_proj_with_mqa", |
| "model.layers.6.self_attn.kv_b_proj", |
| "model.layers.6.self_attn.q_a_proj", |
| "model.layers.7.attn_mhc_module.phi", |
| "model.layers.7.mlp.gate", |
| "model.layers.7.mlp.shared_experts.down_proj", |
| "model.layers.7.mlp.shared_experts.gate_proj", |
| "model.layers.7.mlp.shared_experts.up_proj", |
| "model.layers.7.mlp_mhc_module.phi", |
| "model.layers.7.self_attn.kv_a_proj_with_mqa", |
| "model.layers.7.self_attn.kv_b_proj", |
| "model.layers.7.self_attn.q_a_proj", |
| "model.layers.8.attn_mhc_module.phi", |
| "model.layers.8.mlp.gate", |
| "model.layers.8.mlp.shared_experts.down_proj", |
| "model.layers.8.mlp.shared_experts.gate_proj", |
| "model.layers.8.mlp.shared_experts.up_proj", |
| "model.layers.8.mlp_mhc_module.phi", |
| "model.layers.8.self_attn.kv_a_proj_with_mqa", |
| "model.layers.8.self_attn.kv_b_proj", |
| "model.layers.8.self_attn.q_a_proj", |
| "model.layers.9.attn_mhc_module.phi", |
| "model.layers.9.mlp.gate", |
| "model.layers.9.mlp.shared_experts.down_proj", |
| "model.layers.9.mlp.shared_experts.gate_proj", |
| "model.layers.9.mlp.shared_experts.up_proj", |
| "model.layers.9.mlp_mhc_module.phi", |
| "model.layers.9.self_attn.indexer.weights_proj", |
| "model.layers.9.self_attn.indexer.wk", |
| "model.layers.9.self_attn.indexer.wq_b", |
| "model.layers.9.self_attn.kv_a_proj_with_mqa", |
| "model.layers.9.self_attn.kv_b_proj", |
| "model.layers.9.self_attn.q_a_proj", |
| "model.merge_mhc_module.phi" |
| ], |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "global_compression_ratio": 1.9191, |
| "kv_cache_scheme": null |
| } |
| } |
|
|
