43 lines
990 B
JSON
43 lines
990 B
JSON
{
|
|
"architectures": [
|
|
"Glm4MoeForCausalLM"
|
|
],
|
|
"attention_bias": true,
|
|
"attention_dropout": 0.0,
|
|
"dtype": "float32",
|
|
"eos_token_id": [
|
|
151329,
|
|
151336,
|
|
151338
|
|
],
|
|
"first_k_dense_replace": 1,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 1024,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 2048,
|
|
"max_position_embeddings": 131072,
|
|
"model_type": "glm4_moe",
|
|
"moe_intermediate_size": 256,
|
|
"n_group": 1,
|
|
"n_routed_experts": 8,
|
|
"n_shared_experts": 1,
|
|
"norm_topk_prob": true,
|
|
"num_attention_heads": 16,
|
|
"num_experts_per_tok": 4,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 4,
|
|
"pad_token_id": 151329,
|
|
"partial_rotary_factor": 0.5,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000,
|
|
"routed_scaling_factor": 1.0,
|
|
"tie_word_embeddings": false,
|
|
"topk_group": 1,
|
|
"transformers_version": "4.57.6",
|
|
"use_cache": false,
|
|
"use_grouped_mm": true,
|
|
"use_qk_norm": false,
|
|
"vocab_size": 151552,
|
|
"head_dim": 64
|
|
} |