| { |
| "architectures": [ |
| "GlmMoeDsaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "dtype": "bfloat16", |
| "eos_token_id": [ |
| 154820, |
| 154827, |
| 154829 |
| ], |
| "ep_size": 1, |
| "first_k_dense_replace": 3, |
| "head_dim": 192, |
| "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, |
| "max_position_embeddings": 1048576, |
| "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, |
| "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, |
| "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": "5.12.0", |
| "use_cache": true, |
| "v_head_dim": 256, |
| "vocab_size": 154880, |
| "quantization_config": { |
| "quant_method": "compressed-tensors", |
| "format": "pack-quantized", |
| "quantization_status": "compressed", |
| "config_groups": { |
| "group_0": { |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "num_bits": 4, |
| "type": "int", |
| "symmetric": true, |
| "strategy": "group", |
| "group_size": 32, |
| "dynamic": false, |
| "observer": "mse" |
| }, |
| "input_activations": null, |
| "output_activations": null |
| }, |
| "group_1": { |
| "targets": [ |
| "re:model\\.layers\\.(?:[3-9]|[1-6][0-9]|7[0-7])\\.self_attn\\.(?:q_b_proj|o_proj)$", |
| "re:model\\.layers\\.(?:[3-9]|[1-6][0-9]|7[0-7])\\.mlp\\.shared_experts\\.(?:gate_proj|up_proj|down_proj)$", |
| "re:model\\.layers\\.(?:[3-9]|[1-6][0-9]|7[0-7])\\.mlp\\.shared_experts\\.gate_up_proj$" |
| ], |
| "weights": { |
| "num_bits": 8, |
| "type": "int", |
| "symmetric": true, |
| "strategy": "group", |
| "group_size": 128, |
| "dynamic": false, |
| "observer": "minmax" |
| }, |
| "input_activations": null, |
| "output_activations": null |
| } |
| }, |
| "ignore": [ |
| "lm_head", |
| "re:.*\\.mlp\\.gate\\..*", |
| "re:model\\.layers\\.[012]\\..*", |
| "re:.*embed_tokens.*", |
| "re:.*\\.norm.*", |
| "re:.*layernorm.*", |
| "re:.*self_attn\\.(?:q_a_proj|kv_a_proj_with_mqa|kv_b_proj|fused_qkv_a_proj_with_mqa)$", |
| "re:.*self_attn\\.indexer.*", |
| "re:model\\.layers\\.(?:[0-2]|78)\\.self_attn.*", |
| "re:model\\.layers\\.78\\.mlp\\.shared_experts.*" |
| ] |
| } |
| } |
