| { |
| "architectures": [ |
| "Glm4vMoeTextModel" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "dtype": "float32", |
| "eos_token_id": 151329, |
| "first_k_dense_replace": 1, |
| "hidden_act": "silu", |
| "hidden_size": 16, |
| "initializer_range": 0.02, |
| "intermediate_size": 22, |
| "max_position_embeddings": 512, |
| "model_type": "glm4v_moe_text", |
| "moe_intermediate_size": 1408, |
| "n_group": 1, |
| "n_routed_experts": 8, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 2, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 1, |
| "output_channels": 64, |
| "pad_token_id": 151329, |
| "partial_rotary_factor": 0.5, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "mrope_section": [ |
| 2, |
| 2 |
| ], |
| "partial_rotary_factor": 1.0, |
| "rope_theta": 10000, |
| "rope_type": "default", |
| "type": "default" |
| }, |
| "routed_scaling_factor": 1.0, |
| "router_aux_loss_coef": 0.0001, |
| "tie_word_embeddings": true, |
| "topk_group": 1, |
| "transformers_version": "5.16.0.dev0", |
| "use_cache": true, |
| "vocab_size": 151365 |
| } |
|
|