| { |
| "architectures": [ |
| "GlmMoeDsaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "dtype": "bfloat16", |
| "eos_token_id": [ |
| 154820, |
| 154827, |
| 154829 |
| ], |
| "ep_size": 1, |
| "first_k_dense_replace": 3, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 6144, |
| "index_head_dim": 128, |
| "index_n_heads": 32, |
| "index_share_for_mtp_iteration": true, |
| "index_skip_topk_offset": 3, |
| "index_topk": 2048, |
| "index_topk_freq": 4, |
| "index_topk_pattern": null, |
| "indexer_rope_interleave": true, |
| "indexer_types": [ |
| "full", |
| "full", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared", |
| "shared", |
| "shared" |
| ], |
| "initializer_range": 0.02, |
| "intermediate_size": 12288, |
| "kv_lora_rank": 512, |
| "layer_types": [ |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention", |
| "deepseek_sparse_attention" |
| ], |
| "max_position_embeddings": 1048576, |
| "mlp_bias": false, |
| "mlp_layer_types": [ |
| "dense", |
| "dense", |
| "dense", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse" |
| ], |
| "model_type": "glm_moe_dsa", |
| "moe_intermediate_size": 2048, |
| "moe_layer_freq": 1, |
| "moe_router_dtype": "float32", |
| "n_group": 1, |
| "n_routed_experts": 256, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 78, |
| "num_key_value_heads": 64, |
| "num_nextn_predict_layers": 1, |
| "pad_token_id": 154820, |
| "pretraining_tp": 1, |
| "q_lora_rank": 2048, |
| "qk_head_dim": 256, |
| "qk_nope_head_dim": 192, |
| "qk_rope_head_dim": 64, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": null, |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": true, |
| "group_size": 32, |
| "num_bits": 4, |
| "observer": null, |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.uint8", |
| "strategy": "group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 32, |
| "num_bits": 4, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.uint8", |
| "strategy": "group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "mxfp4-pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "re:^(?!.*mlp\\.expert).*$", |
| "re:.*layers\\.0\\.mlp.*", |
| "re:.*layers\\.1\\.mlp.*", |
| "re:.*layers\\.2\\.mlp.*", |
| "re:.*weights_proj.*", |
| "model.layers.0.mlp.gate_proj", |
| "model.layers.0.mlp.up_proj", |
| "model.layers.0.mlp.down_proj", |
| "model.layers.1.mlp.gate_proj", |
| "model.layers.1.mlp.up_proj", |
| "model.layers.1.mlp.down_proj", |
| "model.layers.2.mlp.gate_proj", |
| "model.layers.2.mlp.up_proj", |
| "model.layers.2.mlp.down_proj", |
| "model.layers.0.self_attn.indexer.weights_proj", |
| "model.layers.1.self_attn.indexer.weights_proj", |
| "model.layers.2.self_attn.indexer.weights_proj", |
| "model.layers.6.self_attn.indexer.weights_proj", |
| "model.layers.10.self_attn.indexer.weights_proj", |
| "model.layers.14.self_attn.indexer.weights_proj", |
| "model.layers.18.self_attn.indexer.weights_proj", |
| "model.layers.22.self_attn.indexer.weights_proj", |
| "model.layers.26.self_attn.indexer.weights_proj", |
| "model.layers.30.self_attn.indexer.weights_proj", |
| "model.layers.34.self_attn.indexer.weights_proj", |
| "model.layers.38.self_attn.indexer.weights_proj", |
| "model.layers.42.self_attn.indexer.weights_proj", |
| "model.layers.46.self_attn.indexer.weights_proj", |
| "model.layers.50.self_attn.indexer.weights_proj", |
| "model.layers.54.self_attn.indexer.weights_proj", |
| "model.layers.58.self_attn.indexer.weights_proj", |
| "model.layers.62.self_attn.indexer.weights_proj", |
| "model.layers.66.self_attn.indexer.weights_proj", |
| "model.layers.70.self_attn.indexer.weights_proj", |
| "model.layers.74.self_attn.indexer.weights_proj", |
| "model.layers.0.self_attn.q_a_proj", |
| "model.layers.0.self_attn.q_b_proj", |
| "model.layers.0.self_attn.kv_a_proj_with_mqa", |
| "model.layers.0.self_attn.kv_b_proj", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.self_attn.indexer.wq_b", |
| "model.layers.0.self_attn.indexer.wk", |
| "model.layers.1.self_attn.q_a_proj", |
| "model.layers.1.self_attn.q_b_proj", |
| "model.layers.1.self_attn.kv_a_proj_with_mqa", |
| "model.layers.1.self_attn.kv_b_proj", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.1.self_attn.indexer.wq_b", |
| "model.layers.1.self_attn.indexer.wk", |
| "model.layers.2.self_attn.q_a_proj", |
| "model.layers.2.self_attn.q_b_proj", |
| "model.layers.2.self_attn.kv_a_proj_with_mqa", |
| "model.layers.2.self_attn.kv_b_proj", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.2.self_attn.indexer.wq_b", |
| "model.layers.2.self_attn.indexer.wk", |
| "model.layers.3.self_attn.q_a_proj", |
| "model.layers.3.self_attn.q_b_proj", |
| "model.layers.3.self_attn.kv_a_proj_with_mqa", |
| "model.layers.3.self_attn.kv_b_proj", |
| "model.layers.3.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.4.self_attn.q_b_proj", |
| "model.layers.4.self_attn.kv_a_proj_with_mqa", |
| "model.layers.4.self_attn.kv_b_proj", |
| "model.layers.4.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.5.self_attn.q_b_proj", |
| "model.layers.5.self_attn.kv_a_proj_with_mqa", |
| "model.layers.5.self_attn.kv_b_proj", |
| "model.layers.5.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.6.self_attn.q_b_proj", |
| "model.layers.6.self_attn.kv_a_proj_with_mqa", |
| "model.layers.6.self_attn.kv_b_proj", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.6.self_attn.indexer.wq_b", |
| "model.layers.6.self_attn.indexer.wk", |
| "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.self_attn.q_a_proj", |
| "model.layers.7.self_attn.q_b_proj", |
| "model.layers.7.self_attn.kv_a_proj_with_mqa", |
| "model.layers.7.self_attn.kv_b_proj", |
| "model.layers.7.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.8.self_attn.q_b_proj", |
| "model.layers.8.self_attn.kv_a_proj_with_mqa", |
| "model.layers.8.self_attn.kv_b_proj", |
| "model.layers.8.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.9.self_attn.q_b_proj", |
| "model.layers.9.self_attn.kv_a_proj_with_mqa", |
| "model.layers.9.self_attn.kv_b_proj", |
| "model.layers.9.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.10.self_attn.q_b_proj", |
| "model.layers.10.self_attn.kv_a_proj_with_mqa", |
| "model.layers.10.self_attn.kv_b_proj", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.10.self_attn.indexer.wq_b", |
| "model.layers.10.self_attn.indexer.wk", |
| "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.self_attn.q_a_proj", |
| "model.layers.11.self_attn.q_b_proj", |
| "model.layers.11.self_attn.kv_a_proj_with_mqa", |
| "model.layers.11.self_attn.kv_b_proj", |
| "model.layers.11.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.12.self_attn.q_b_proj", |
| "model.layers.12.self_attn.kv_a_proj_with_mqa", |
| "model.layers.12.self_attn.kv_b_proj", |
| "model.layers.12.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.13.self_attn.q_b_proj", |
| "model.layers.13.self_attn.kv_a_proj_with_mqa", |
| "model.layers.13.self_attn.kv_b_proj", |
| "model.layers.13.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.14.self_attn.q_b_proj", |
| "model.layers.14.self_attn.kv_a_proj_with_mqa", |
| "model.layers.14.self_attn.kv_b_proj", |
| "model.layers.14.self_attn.o_proj", |
| "model.layers.14.self_attn.indexer.wq_b", |
| "model.layers.14.self_attn.indexer.wk", |
| "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.self_attn.q_a_proj", |
| "model.layers.15.self_attn.q_b_proj", |
| "model.layers.15.self_attn.kv_a_proj_with_mqa", |
| "model.layers.15.self_attn.kv_b_proj", |
| "model.layers.15.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.16.self_attn.q_b_proj", |
| "model.layers.16.self_attn.kv_a_proj_with_mqa", |
| "model.layers.16.self_attn.kv_b_proj", |
| "model.layers.16.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.17.self_attn.q_b_proj", |
| "model.layers.17.self_attn.kv_a_proj_with_mqa", |
| "model.layers.17.self_attn.kv_b_proj", |
| "model.layers.17.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.18.self_attn.q_b_proj", |
| "model.layers.18.self_attn.kv_a_proj_with_mqa", |
| "model.layers.18.self_attn.kv_b_proj", |
| "model.layers.18.self_attn.o_proj", |
| "model.layers.18.self_attn.indexer.wq_b", |
| "model.layers.18.self_attn.indexer.wk", |
| "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.self_attn.q_a_proj", |
| "model.layers.19.self_attn.q_b_proj", |
| "model.layers.19.self_attn.kv_a_proj_with_mqa", |
| "model.layers.19.self_attn.kv_b_proj", |
| "model.layers.19.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.20.self_attn.q_b_proj", |
| "model.layers.20.self_attn.kv_a_proj_with_mqa", |
| "model.layers.20.self_attn.kv_b_proj", |
| "model.layers.20.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.21.self_attn.q_b_proj", |
| "model.layers.21.self_attn.kv_a_proj_with_mqa", |
| "model.layers.21.self_attn.kv_b_proj", |
| "model.layers.21.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.22.self_attn.q_b_proj", |
| "model.layers.22.self_attn.kv_a_proj_with_mqa", |
| "model.layers.22.self_attn.kv_b_proj", |
| "model.layers.22.self_attn.o_proj", |
| "model.layers.22.self_attn.indexer.wq_b", |
| "model.layers.22.self_attn.indexer.wk", |
| "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.self_attn.q_a_proj", |
| "model.layers.23.self_attn.q_b_proj", |
| "model.layers.23.self_attn.kv_a_proj_with_mqa", |
| "model.layers.23.self_attn.kv_b_proj", |
| "model.layers.23.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.24.self_attn.q_b_proj", |
| "model.layers.24.self_attn.kv_a_proj_with_mqa", |
| "model.layers.24.self_attn.kv_b_proj", |
| "model.layers.24.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.25.self_attn.q_b_proj", |
| "model.layers.25.self_attn.kv_a_proj_with_mqa", |
| "model.layers.25.self_attn.kv_b_proj", |
| "model.layers.25.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.26.self_attn.q_b_proj", |
| "model.layers.26.self_attn.kv_a_proj_with_mqa", |
| "model.layers.26.self_attn.kv_b_proj", |
| "model.layers.26.self_attn.o_proj", |
| "model.layers.26.self_attn.indexer.wq_b", |
| "model.layers.26.self_attn.indexer.wk", |
| "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.self_attn.q_a_proj", |
| "model.layers.27.self_attn.q_b_proj", |
| "model.layers.27.self_attn.kv_a_proj_with_mqa", |
| "model.layers.27.self_attn.kv_b_proj", |
| "model.layers.27.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.28.self_attn.q_b_proj", |
| "model.layers.28.self_attn.kv_a_proj_with_mqa", |
| "model.layers.28.self_attn.kv_b_proj", |
| "model.layers.28.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.29.self_attn.q_b_proj", |
| "model.layers.29.self_attn.kv_a_proj_with_mqa", |
| "model.layers.29.self_attn.kv_b_proj", |
| "model.layers.29.self_attn.o_proj", |
| "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.self_attn.q_a_proj", |
| "model.layers.30.self_attn.q_b_proj", |
| "model.layers.30.self_attn.kv_a_proj_with_mqa", |
| "model.layers.30.self_attn.kv_b_proj", |
| "model.layers.30.self_attn.o_proj", |
| "model.layers.30.self_attn.indexer.wq_b", |
| "model.layers.30.self_attn.indexer.wk", |
| "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.self_attn.q_a_proj", |
| "model.layers.31.self_attn.q_b_proj", |
| "model.layers.31.self_attn.kv_a_proj_with_mqa", |
| "model.layers.31.self_attn.kv_b_proj", |
| "model.layers.31.self_attn.o_proj", |
| "model.layers.31.mlp.shared_experts.gate_proj", |
| "model.layers.31.mlp.shared_experts.up_proj", |
| "model.layers.31.mlp.shared_experts.down_proj", |
| "model.layers.32.self_attn.q_a_proj", |
| "model.layers.32.self_attn.q_b_proj", |
| "model.layers.32.self_attn.kv_a_proj_with_mqa", |
| "model.layers.32.self_attn.kv_b_proj", |
| "model.layers.32.self_attn.o_proj", |
| "model.layers.32.mlp.shared_experts.gate_proj", |
| "model.layers.32.mlp.shared_experts.up_proj", |
| "model.layers.32.mlp.shared_experts.down_proj", |
| "model.layers.33.self_attn.q_a_proj", |
| "model.layers.33.self_attn.q_b_proj", |
| "model.layers.33.self_attn.kv_a_proj_with_mqa", |
| "model.layers.33.self_attn.kv_b_proj", |
| "model.layers.33.self_attn.o_proj", |
| "model.layers.33.mlp.shared_experts.gate_proj", |
| "model.layers.33.mlp.shared_experts.up_proj", |
| "model.layers.33.mlp.shared_experts.down_proj", |
| "model.layers.34.self_attn.q_a_proj", |
| "model.layers.34.self_attn.q_b_proj", |
| "model.layers.34.self_attn.kv_a_proj_with_mqa", |
| "model.layers.34.self_attn.kv_b_proj", |
| "model.layers.34.self_attn.o_proj", |
| "model.layers.34.self_attn.indexer.wq_b", |
| "model.layers.34.self_attn.indexer.wk", |
| "model.layers.34.mlp.shared_experts.gate_proj", |
| "model.layers.34.mlp.shared_experts.up_proj", |
| "model.layers.34.mlp.shared_experts.down_proj", |
| "model.layers.35.self_attn.q_a_proj", |
| "model.layers.35.self_attn.q_b_proj", |
| "model.layers.35.self_attn.kv_a_proj_with_mqa", |
| "model.layers.35.self_attn.kv_b_proj", |
| "model.layers.35.self_attn.o_proj", |
| "model.layers.35.mlp.shared_experts.gate_proj", |
| "model.layers.35.mlp.shared_experts.up_proj", |
| "model.layers.35.mlp.shared_experts.down_proj", |
| "model.layers.36.self_attn.q_a_proj", |
| "model.layers.36.self_attn.q_b_proj", |
| "model.layers.36.self_attn.kv_a_proj_with_mqa", |
| "model.layers.36.self_attn.kv_b_proj", |
| "model.layers.36.self_attn.o_proj", |
| "model.layers.36.mlp.shared_experts.gate_proj", |
| "model.layers.36.mlp.shared_experts.up_proj", |
| "model.layers.36.mlp.shared_experts.down_proj", |
| "model.layers.37.self_attn.q_a_proj", |
| "model.layers.37.self_attn.q_b_proj", |
| "model.layers.37.self_attn.kv_a_proj_with_mqa", |
| "model.layers.37.self_attn.kv_b_proj", |
| "model.layers.37.self_attn.o_proj", |
| "model.layers.37.mlp.shared_experts.gate_proj", |
| "model.layers.37.mlp.shared_experts.up_proj", |
| "model.layers.37.mlp.shared_experts.down_proj", |
| "model.layers.38.self_attn.q_a_proj", |
| "model.layers.38.self_attn.q_b_proj", |
| "model.layers.38.self_attn.kv_a_proj_with_mqa", |
| "model.layers.38.self_attn.kv_b_proj", |
| "model.layers.38.self_attn.o_proj", |
| "model.layers.38.self_attn.indexer.wq_b", |
| "model.layers.38.self_attn.indexer.wk", |
| "model.layers.38.mlp.shared_experts.gate_proj", |
| "model.layers.38.mlp.shared_experts.up_proj", |
| "model.layers.38.mlp.shared_experts.down_proj", |
| "model.layers.39.self_attn.q_a_proj", |
| "model.layers.39.self_attn.q_b_proj", |
| "model.layers.39.self_attn.kv_a_proj_with_mqa", |
| "model.layers.39.self_attn.kv_b_proj", |
| "model.layers.39.self_attn.o_proj", |
| "model.layers.39.mlp.shared_experts.gate_proj", |
| "model.layers.39.mlp.shared_experts.up_proj", |
| "model.layers.39.mlp.shared_experts.down_proj", |
| "model.layers.40.self_attn.q_a_proj", |
| "model.layers.40.self_attn.q_b_proj", |
| "model.layers.40.self_attn.kv_a_proj_with_mqa", |
| "model.layers.40.self_attn.kv_b_proj", |
| "model.layers.40.self_attn.o_proj", |
| "model.layers.40.mlp.shared_experts.gate_proj", |
| "model.layers.40.mlp.shared_experts.up_proj", |
| "model.layers.40.mlp.shared_experts.down_proj", |
| "model.layers.41.self_attn.q_a_proj", |
| "model.layers.41.self_attn.q_b_proj", |
| "model.layers.41.self_attn.kv_a_proj_with_mqa", |
| "model.layers.41.self_attn.kv_b_proj", |
| "model.layers.41.self_attn.o_proj", |
| "model.layers.41.mlp.shared_experts.gate_proj", |
| "model.layers.41.mlp.shared_experts.up_proj", |
| "model.layers.41.mlp.shared_experts.down_proj", |
| "model.layers.42.self_attn.q_a_proj", |
| "model.layers.42.self_attn.q_b_proj", |
| "model.layers.42.self_attn.kv_a_proj_with_mqa", |
| "model.layers.42.self_attn.kv_b_proj", |
| "model.layers.42.self_attn.o_proj", |
| "model.layers.42.self_attn.indexer.wq_b", |
| "model.layers.42.self_attn.indexer.wk", |
| "model.layers.42.mlp.shared_experts.gate_proj", |
| "model.layers.42.mlp.shared_experts.up_proj", |
| "model.layers.42.mlp.shared_experts.down_proj", |
| "model.layers.43.self_attn.q_a_proj", |
| "model.layers.43.self_attn.q_b_proj", |
| "model.layers.43.self_attn.kv_a_proj_with_mqa", |
| "model.layers.43.self_attn.kv_b_proj", |
| "model.layers.43.self_attn.o_proj", |
| "model.layers.43.mlp.shared_experts.gate_proj", |
| "model.layers.43.mlp.shared_experts.up_proj", |
| "model.layers.43.mlp.shared_experts.down_proj", |
| "model.layers.44.self_attn.q_a_proj", |
| "model.layers.44.self_attn.q_b_proj", |
| "model.layers.44.self_attn.kv_a_proj_with_mqa", |
| "model.layers.44.self_attn.kv_b_proj", |
| "model.layers.44.self_attn.o_proj", |
| "model.layers.44.mlp.shared_experts.gate_proj", |
| "model.layers.44.mlp.shared_experts.up_proj", |
| "model.layers.44.mlp.shared_experts.down_proj", |
| "model.layers.45.self_attn.q_a_proj", |
| "model.layers.45.self_attn.q_b_proj", |
| "model.layers.45.self_attn.kv_a_proj_with_mqa", |
| "model.layers.45.self_attn.kv_b_proj", |
| "model.layers.45.self_attn.o_proj", |
| "model.layers.45.mlp.shared_experts.gate_proj", |
| "model.layers.45.mlp.shared_experts.up_proj", |
| "model.layers.45.mlp.shared_experts.down_proj", |
| "model.layers.46.self_attn.q_a_proj", |
| "model.layers.46.self_attn.q_b_proj", |
| "model.layers.46.self_attn.kv_a_proj_with_mqa", |
| "model.layers.46.self_attn.kv_b_proj", |
| "model.layers.46.self_attn.o_proj", |
| "model.layers.46.self_attn.indexer.wq_b", |
| "model.layers.46.self_attn.indexer.wk", |
| "model.layers.46.mlp.shared_experts.gate_proj", |
| "model.layers.46.mlp.shared_experts.up_proj", |
| "model.layers.46.mlp.shared_experts.down_proj", |
| "model.layers.47.self_attn.q_a_proj", |
| "model.layers.47.self_attn.q_b_proj", |
| "model.layers.47.self_attn.kv_a_proj_with_mqa", |
| "model.layers.47.self_attn.kv_b_proj", |
| "model.layers.47.self_attn.o_proj", |
| "model.layers.47.mlp.shared_experts.gate_proj", |
| "model.layers.47.mlp.shared_experts.up_proj", |
| "model.layers.47.mlp.shared_experts.down_proj", |
| "model.layers.48.self_attn.q_a_proj", |
| "model.layers.48.self_attn.q_b_proj", |
| "model.layers.48.self_attn.kv_a_proj_with_mqa", |
| "model.layers.48.self_attn.kv_b_proj", |
| "model.layers.48.self_attn.o_proj", |
| "model.layers.48.mlp.shared_experts.gate_proj", |
| "model.layers.48.mlp.shared_experts.up_proj", |
| "model.layers.48.mlp.shared_experts.down_proj", |
| "model.layers.49.self_attn.q_a_proj", |
| "model.layers.49.self_attn.q_b_proj", |
| "model.layers.49.self_attn.kv_a_proj_with_mqa", |
| "model.layers.49.self_attn.kv_b_proj", |
| "model.layers.49.self_attn.o_proj", |
| "model.layers.49.mlp.shared_experts.gate_proj", |
| "model.layers.49.mlp.shared_experts.up_proj", |
| "model.layers.49.mlp.shared_experts.down_proj", |
| "model.layers.50.self_attn.q_a_proj", |
| "model.layers.50.self_attn.q_b_proj", |
| "model.layers.50.self_attn.kv_a_proj_with_mqa", |
| "model.layers.50.self_attn.kv_b_proj", |
| "model.layers.50.self_attn.o_proj", |
| "model.layers.50.self_attn.indexer.wq_b", |
| "model.layers.50.self_attn.indexer.wk", |
| "model.layers.50.mlp.shared_experts.gate_proj", |
| "model.layers.50.mlp.shared_experts.up_proj", |
| "model.layers.50.mlp.shared_experts.down_proj", |
| "model.layers.51.self_attn.q_a_proj", |
| "model.layers.51.self_attn.q_b_proj", |
| "model.layers.51.self_attn.kv_a_proj_with_mqa", |
| "model.layers.51.self_attn.kv_b_proj", |
| "model.layers.51.self_attn.o_proj", |
| "model.layers.51.mlp.shared_experts.gate_proj", |
| "model.layers.51.mlp.shared_experts.up_proj", |
| "model.layers.51.mlp.shared_experts.down_proj", |
| "model.layers.52.self_attn.q_a_proj", |
| "model.layers.52.self_attn.q_b_proj", |
| "model.layers.52.self_attn.kv_a_proj_with_mqa", |
| "model.layers.52.self_attn.kv_b_proj", |
| "model.layers.52.self_attn.o_proj", |
| "model.layers.52.mlp.shared_experts.gate_proj", |
| "model.layers.52.mlp.shared_experts.up_proj", |
| "model.layers.52.mlp.shared_experts.down_proj", |
| "model.layers.53.self_attn.q_a_proj", |
| "model.layers.53.self_attn.q_b_proj", |
| "model.layers.53.self_attn.kv_a_proj_with_mqa", |
| "model.layers.53.self_attn.kv_b_proj", |
| "model.layers.53.self_attn.o_proj", |
| "model.layers.53.mlp.shared_experts.gate_proj", |
| "model.layers.53.mlp.shared_experts.up_proj", |
| "model.layers.53.mlp.shared_experts.down_proj", |
| "model.layers.54.self_attn.q_a_proj", |
| "model.layers.54.self_attn.q_b_proj", |
| "model.layers.54.self_attn.kv_a_proj_with_mqa", |
| "model.layers.54.self_attn.kv_b_proj", |
| "model.layers.54.self_attn.o_proj", |
| "model.layers.54.self_attn.indexer.wq_b", |
| "model.layers.54.self_attn.indexer.wk", |
| "model.layers.54.mlp.shared_experts.gate_proj", |
| "model.layers.54.mlp.shared_experts.up_proj", |
| "model.layers.54.mlp.shared_experts.down_proj", |
| "model.layers.55.self_attn.q_a_proj", |
| "model.layers.55.self_attn.q_b_proj", |
| "model.layers.55.self_attn.kv_a_proj_with_mqa", |
| "model.layers.55.self_attn.kv_b_proj", |
| "model.layers.55.self_attn.o_proj", |
| "model.layers.55.mlp.shared_experts.gate_proj", |
| "model.layers.55.mlp.shared_experts.up_proj", |
| "model.layers.55.mlp.shared_experts.down_proj", |
| "model.layers.56.self_attn.q_a_proj", |
| "model.layers.56.self_attn.q_b_proj", |
| "model.layers.56.self_attn.kv_a_proj_with_mqa", |
| "model.layers.56.self_attn.kv_b_proj", |
| "model.layers.56.self_attn.o_proj", |
| "model.layers.56.mlp.shared_experts.gate_proj", |
| "model.layers.56.mlp.shared_experts.up_proj", |
| "model.layers.56.mlp.shared_experts.down_proj", |
| "model.layers.57.self_attn.q_a_proj", |
| "model.layers.57.self_attn.q_b_proj", |
| "model.layers.57.self_attn.kv_a_proj_with_mqa", |
| "model.layers.57.self_attn.kv_b_proj", |
| "model.layers.57.self_attn.o_proj", |
| "model.layers.57.mlp.shared_experts.gate_proj", |
| "model.layers.57.mlp.shared_experts.up_proj", |
| "model.layers.57.mlp.shared_experts.down_proj", |
| "model.layers.58.self_attn.q_a_proj", |
| "model.layers.58.self_attn.q_b_proj", |
| "model.layers.58.self_attn.kv_a_proj_with_mqa", |
| "model.layers.58.self_attn.kv_b_proj", |
| "model.layers.58.self_attn.o_proj", |
| "model.layers.58.self_attn.indexer.wq_b", |
| "model.layers.58.self_attn.indexer.wk", |
| "model.layers.58.mlp.shared_experts.gate_proj", |
| "model.layers.58.mlp.shared_experts.up_proj", |
| "model.layers.58.mlp.shared_experts.down_proj", |
| "model.layers.59.self_attn.q_a_proj", |
| "model.layers.59.self_attn.q_b_proj", |
| "model.layers.59.self_attn.kv_a_proj_with_mqa", |
| "model.layers.59.self_attn.kv_b_proj", |
| "model.layers.59.self_attn.o_proj", |
| "model.layers.59.mlp.shared_experts.gate_proj", |
| "model.layers.59.mlp.shared_experts.up_proj", |
| "model.layers.59.mlp.shared_experts.down_proj", |
| "model.layers.60.self_attn.q_a_proj", |
| "model.layers.60.self_attn.q_b_proj", |
| "model.layers.60.self_attn.kv_a_proj_with_mqa", |
| "model.layers.60.self_attn.kv_b_proj", |
| "model.layers.60.self_attn.o_proj", |
| "model.layers.60.mlp.shared_experts.gate_proj", |
| "model.layers.60.mlp.shared_experts.up_proj", |
| "model.layers.60.mlp.shared_experts.down_proj", |
| "model.layers.61.self_attn.q_a_proj", |
| "model.layers.61.self_attn.q_b_proj", |
| "model.layers.61.self_attn.kv_a_proj_with_mqa", |
| "model.layers.61.self_attn.kv_b_proj", |
| "model.layers.61.self_attn.o_proj", |
| "model.layers.61.mlp.shared_experts.gate_proj", |
| "model.layers.61.mlp.shared_experts.up_proj", |
| "model.layers.61.mlp.shared_experts.down_proj", |
| "model.layers.62.self_attn.q_a_proj", |
| "model.layers.62.self_attn.q_b_proj", |
| "model.layers.62.self_attn.kv_a_proj_with_mqa", |
| "model.layers.62.self_attn.kv_b_proj", |
| "model.layers.62.self_attn.o_proj", |
| "model.layers.62.self_attn.indexer.wq_b", |
| "model.layers.62.self_attn.indexer.wk", |
| "model.layers.62.mlp.shared_experts.gate_proj", |
| "model.layers.62.mlp.shared_experts.up_proj", |
| "model.layers.62.mlp.shared_experts.down_proj", |
| "model.layers.63.self_attn.q_a_proj", |
| "model.layers.63.self_attn.q_b_proj", |
| "model.layers.63.self_attn.kv_a_proj_with_mqa", |
| "model.layers.63.self_attn.kv_b_proj", |
| "model.layers.63.self_attn.o_proj", |
| "model.layers.63.mlp.shared_experts.gate_proj", |
| "model.layers.63.mlp.shared_experts.up_proj", |
| "model.layers.63.mlp.shared_experts.down_proj", |
| "model.layers.64.self_attn.q_a_proj", |
| "model.layers.64.self_attn.q_b_proj", |
| "model.layers.64.self_attn.kv_a_proj_with_mqa", |
| "model.layers.64.self_attn.kv_b_proj", |
| "model.layers.64.self_attn.o_proj", |
| "model.layers.64.mlp.shared_experts.gate_proj", |
| "model.layers.64.mlp.shared_experts.up_proj", |
| "model.layers.64.mlp.shared_experts.down_proj", |
| "model.layers.65.self_attn.q_a_proj", |
| "model.layers.65.self_attn.q_b_proj", |
| "model.layers.65.self_attn.kv_a_proj_with_mqa", |
| "model.layers.65.self_attn.kv_b_proj", |
| "model.layers.65.self_attn.o_proj", |
| "model.layers.65.mlp.shared_experts.gate_proj", |
| "model.layers.65.mlp.shared_experts.up_proj", |
| "model.layers.65.mlp.shared_experts.down_proj", |
| "model.layers.66.self_attn.q_a_proj", |
| "model.layers.66.self_attn.q_b_proj", |
| "model.layers.66.self_attn.kv_a_proj_with_mqa", |
| "model.layers.66.self_attn.kv_b_proj", |
| "model.layers.66.self_attn.o_proj", |
| "model.layers.66.self_attn.indexer.wq_b", |
| "model.layers.66.self_attn.indexer.wk", |
| "model.layers.66.mlp.shared_experts.gate_proj", |
| "model.layers.66.mlp.shared_experts.up_proj", |
| "model.layers.66.mlp.shared_experts.down_proj", |
| "model.layers.67.self_attn.q_a_proj", |
| "model.layers.67.self_attn.q_b_proj", |
| "model.layers.67.self_attn.kv_a_proj_with_mqa", |
| "model.layers.67.self_attn.kv_b_proj", |
| "model.layers.67.self_attn.o_proj", |
| "model.layers.67.mlp.shared_experts.gate_proj", |
| "model.layers.67.mlp.shared_experts.up_proj", |
| "model.layers.67.mlp.shared_experts.down_proj", |
| "model.layers.68.self_attn.q_a_proj", |
| "model.layers.68.self_attn.q_b_proj", |
| "model.layers.68.self_attn.kv_a_proj_with_mqa", |
| "model.layers.68.self_attn.kv_b_proj", |
| "model.layers.68.self_attn.o_proj", |
| "model.layers.68.mlp.shared_experts.gate_proj", |
| "model.layers.68.mlp.shared_experts.up_proj", |
| "model.layers.68.mlp.shared_experts.down_proj", |
| "model.layers.69.self_attn.q_a_proj", |
| "model.layers.69.self_attn.q_b_proj", |
| "model.layers.69.self_attn.kv_a_proj_with_mqa", |
| "model.layers.69.self_attn.kv_b_proj", |
| "model.layers.69.self_attn.o_proj", |
| "model.layers.69.mlp.shared_experts.gate_proj", |
| "model.layers.69.mlp.shared_experts.up_proj", |
| "model.layers.69.mlp.shared_experts.down_proj", |
| "model.layers.70.self_attn.q_a_proj", |
| "model.layers.70.self_attn.q_b_proj", |
| "model.layers.70.self_attn.kv_a_proj_with_mqa", |
| "model.layers.70.self_attn.kv_b_proj", |
| "model.layers.70.self_attn.o_proj", |
| "model.layers.70.self_attn.indexer.wq_b", |
| "model.layers.70.self_attn.indexer.wk", |
| "model.layers.70.mlp.shared_experts.gate_proj", |
| "model.layers.70.mlp.shared_experts.up_proj", |
| "model.layers.70.mlp.shared_experts.down_proj", |
| "model.layers.71.self_attn.q_a_proj", |
| "model.layers.71.self_attn.q_b_proj", |
| "model.layers.71.self_attn.kv_a_proj_with_mqa", |
| "model.layers.71.self_attn.kv_b_proj", |
| "model.layers.71.self_attn.o_proj", |
| "model.layers.71.mlp.shared_experts.gate_proj", |
| "model.layers.71.mlp.shared_experts.up_proj", |
| "model.layers.71.mlp.shared_experts.down_proj", |
| "model.layers.72.self_attn.q_a_proj", |
| "model.layers.72.self_attn.q_b_proj", |
| "model.layers.72.self_attn.kv_a_proj_with_mqa", |
| "model.layers.72.self_attn.kv_b_proj", |
| "model.layers.72.self_attn.o_proj", |
| "model.layers.72.mlp.shared_experts.gate_proj", |
| "model.layers.72.mlp.shared_experts.up_proj", |
| "model.layers.72.mlp.shared_experts.down_proj", |
| "model.layers.73.self_attn.q_a_proj", |
| "model.layers.73.self_attn.q_b_proj", |
| "model.layers.73.self_attn.kv_a_proj_with_mqa", |
| "model.layers.73.self_attn.kv_b_proj", |
| "model.layers.73.self_attn.o_proj", |
| "model.layers.73.mlp.shared_experts.gate_proj", |
| "model.layers.73.mlp.shared_experts.up_proj", |
| "model.layers.73.mlp.shared_experts.down_proj", |
| "model.layers.74.self_attn.q_a_proj", |
| "model.layers.74.self_attn.q_b_proj", |
| "model.layers.74.self_attn.kv_a_proj_with_mqa", |
| "model.layers.74.self_attn.kv_b_proj", |
| "model.layers.74.self_attn.o_proj", |
| "model.layers.74.self_attn.indexer.wq_b", |
| "model.layers.74.self_attn.indexer.wk", |
| "model.layers.74.mlp.shared_experts.gate_proj", |
| "model.layers.74.mlp.shared_experts.up_proj", |
| "model.layers.74.mlp.shared_experts.down_proj", |
| "model.layers.75.self_attn.q_a_proj", |
| "model.layers.75.self_attn.q_b_proj", |
| "model.layers.75.self_attn.kv_a_proj_with_mqa", |
| "model.layers.75.self_attn.kv_b_proj", |
| "model.layers.75.self_attn.o_proj", |
| "model.layers.75.mlp.shared_experts.gate_proj", |
| "model.layers.75.mlp.shared_experts.up_proj", |
| "model.layers.75.mlp.shared_experts.down_proj", |
| "model.layers.76.self_attn.q_a_proj", |
| "model.layers.76.self_attn.q_b_proj", |
| "model.layers.76.self_attn.kv_a_proj_with_mqa", |
| "model.layers.76.self_attn.kv_b_proj", |
| "model.layers.76.self_attn.o_proj", |
| "model.layers.76.mlp.shared_experts.gate_proj", |
| "model.layers.76.mlp.shared_experts.up_proj", |
| "model.layers.76.mlp.shared_experts.down_proj", |
| "model.layers.77.self_attn.q_a_proj", |
| "model.layers.77.self_attn.q_b_proj", |
| "model.layers.77.self_attn.kv_a_proj_with_mqa", |
| "model.layers.77.self_attn.kv_b_proj", |
| "model.layers.77.self_attn.o_proj", |
| "model.layers.77.mlp.shared_experts.gate_proj", |
| "model.layers.77.mlp.shared_experts.up_proj", |
| "model.layers.77.mlp.shared_experts.down_proj", |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "provider": "auto-round", |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_interleave": true, |
| "rope_parameters": { |
| "rope_theta": 8000000, |
| "rope_type": "default" |
| }, |
| "routed_scaling_factor": 2.5, |
| "scoring_func": "sigmoid", |
| "tie_word_embeddings": false, |
| "topk_group": 1, |
| "topk_method": "noaux_tc", |
| "transformers_version": "5.14.1", |
| "use_cache": true, |
| "v_head_dim": 256, |
| "vocab_size": 154880 |
| } |
|
|