| { |
| "architectures": [ |
| "GlmMoeDsaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "dtype": "bfloat16", |
| "eos_token_id": [ |
| 1, |
| 2, |
| 3 |
| ], |
| "ep_size": 1, |
| "first_k_dense_replace": 1, |
| "hidden_act": "silu", |
| "hidden_size": 512, |
| "index_head_dim": 128, |
| "index_n_heads": 32, |
| "index_share_for_mtp_iteration": true, |
| "index_skip_topk_offset": 3, |
| "index_topk": 128, |
| "index_topk_freq": 4, |
| "index_topk_pattern": null, |
| "indexer_rope_interleave": true, |
| "indexer_types": [ |
| "full", |
| "full", |
| "full", |
| "shared", |
| "shared", |
| "shared", |
| "full", |
| "shared" |
| ], |
| "initializer_range": 0.02, |
| "intermediate_size": 1024, |
| "kv_lora_rank": 512, |
| "max_position_embeddings": 1048576, |
| "mlp_layer_types": [ |
| "dense", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse" |
| ], |
| "model_type": "glm_moe_dsa", |
| "moe_intermediate_size": 128, |
| "moe_layer_freq": 1, |
| "n_group": 1, |
| "n_routed_experts": 4, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 8, |
| "num_key_value_heads": 64, |
| "num_nextn_predict_layers": 0, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "q_lora_rank": 128, |
| "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": "5.8.1", |
| "use_cache": true, |
| "v_head_dim": 512, |
| "vocab_size": 2048 |
| } |
|
|
