Files
llm-jp-4-32b-a3b-base/config.json
ModelHub XC 49a2e94074 初始化项目,由ModelHub XC社区提供模型
Model: llm-jp/llm-jp-4-32b-a3b-base
Source: Original Platform
2026-05-13 05:44:32 +08:00

40 lines
967 B
JSON

{
"architectures": [
"Qwen3MoeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"decoder_sparse_step": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.006,
"intermediate_size": 7680,
"max_position_embeddings": 65536,
"max_window_layers": 32,
"mlp_only_layers": [],
"model_type": "qwen3_moe",
"moe_intermediate_size": 960,
"norm_topk_prob": true,
"num_attention_heads": 40,
"num_experts": 128,
"num_experts_per_tok": 8,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"output_router_logits": false,
"pad_token_id": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 500000,
"router_aux_loss_coef": 0.01,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.56.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 196608
}