{ "_from_model_config": true, "architectures": [ "YuanForCausalLM" ], "auto_map":{ "AutoConfig": "configuration_yuan.YuanConfig", "AutoModelForCausalLM": "yuan_hf_model.YuanForCausalLM" }, "tokenizer_class": "YuanTokenizer", "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 4096, "model_type": "yuan", "num_attention_heads": 16, "num_hidden_layers": 24, "rms_norm_eps": 1e-06, "dropout": 0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.30.0.dev0", "use_cache": true, "causal_mask": true, "use_flash_attention": true, "reset_attention_mask": true, "reset_position_ids": true, "use_loss_mask": false, "use_moe": true, "moe_config":{ "moe_num_experts": 32, "moe_top_k": 2, "ffn_hidden_size": 8192, "norm_topk_prob":true, "gated_linear_unit":true }, "eod_token": 77185, "sep_token": 77187, "eod_token_id": 77185, "sep_token_id": 77185, "pad_token_id": 77185, "bos_token_id": 77185, "eos_token_id": 77185, "mask_token_id": 77185, "vocab_size": 135040, "attention_projection_size": 4096, "reset_attention_mask": false, "output_router_logits": true }