dinhosms/NeMoE-8x12B-Random-Experts
214
1{2 "architectures": [3 "MixtralForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 1,7 "dtype": "bfloat16",8 "eos_token_id": 2,9 "head_dim": 128,10 "hidden_act": "silu",11 "hidden_size": 5120,12 "initializer_range": 0.02,13 "intermediate_size": 14336,14 "max_position_embeddings": 1024000,15 "model_type": "mixtral",16 "num_attention_heads": 32,17 "num_experts_per_tok": 2,18 "num_hidden_layers": 40,19 "num_key_value_heads": 8,20 "num_local_experts": 8,21 "output_router_logits": false,22 "pad_token_id": 10,23 "rms_norm_eps": 1e-05,24 "rope_theta": 1000000.0,25 "router_aux_loss_coef": 0.001,26 "router_jitter_noise": 0.0,27 "sliding_window": null,28 "tie_word_embeddings": false,29 "transformers_version": "4.57.1",30 "unsloth_version": "2024.8",31 "use_cache": true,32 "vocab_size": 13107233}34 