Files
ModelHub XC d0353dd27b 初始化项目,由ModelHub XC社区提供模型
Model: FlameF0X/TinyMoE-100m-2x8-chat-stage1
Source: Original Platform
2026-08-17 20:12:17 +08:00

36 lines
825 B
JSON

{
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": null,
"hidden_act": "silu",
"hidden_size": 384,
"initializer_range": 0.02,
"intermediate_size": 768,
"max_position_embeddings": 4096,
"model_type": "mixtral",
"num_attention_heads": 8,
"num_experts_per_tok": 2,
"num_hidden_layers": 10,
"num_key_value_heads": 4,
"num_local_experts": 8,
"output_router_logits": true,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"factor": 4.0,
"type": "linear"
},
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.02,
"router_jitter_noise": 0.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.55.0",
"use_cache": false,
"vocab_size": 32003
}