hf-tiny-v2/tiny-random-Qwen2MoeForSequenceClassification
013
1{2 "architectures": [3 "Qwen2MoeForSequenceClassification"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 1,7 "decoder_sparse_step": 1,8 "dtype": "float32",9 "eos_token_id": 151643,10 "hidden_act": "gelu",11 "hidden_size": 32,12 "initializer_range": 0.02,13 "intermediate_size": 32,14 "layer_types": [15 "full_attention",16 "full_attention"17 ],18 "max_position_embeddings": 512,19 "max_window_layers": 28,20 "mlp_only_layers": [],21 "model_type": "qwen2_moe",22 "moe_intermediate_size": 16,23 "norm_topk_prob": false,24 "num_attention_heads": 2,25 "num_experts": 8,26 "num_experts_per_tok": 2,27 "num_hidden_layers": 2,28 "num_key_value_heads": 2,29 "output_router_logits": false,30 "pad_token_id": 151643,31 "qkv_bias": true,32 "rms_norm_eps": 1e-06,33 "rope_parameters": {34 "rope_theta": 10000.0,35 "rope_type": "default"36 },37 "router_aux_loss_coef": 0.001,38 "shared_expert_intermediate_size": 36,39 "sliding_window": 0,40 "tie_word_embeddings": false,41 "transformers_version": "5.16.0.dev0",42 "use_cache": true,43 "use_sliding_window": false,44 "vocab_size": 15164645}46 