Plaban81/Moe-4x7b-math-reason-code

1{2  "_name_or_path": "merge/",3  "architectures": [4    "MixtralForCausalLM"5  ],6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "eos_token_id": 2,9  "hidden_act": "silu",10  "hidden_size": 4096,11  "initializer_range": 0.02,12  "intermediate_size": 14336,13  "max_position_embeddings": 32768,14  "model_type": "mixtral",15  "num_attention_heads": 32,16  "num_experts_per_tok": 2,17  "num_hidden_layers": 32,18  "num_key_value_heads": 8,19  "num_local_experts": 4,20  "output_router_logits": false,21  "rms_norm_eps": 1e-05,22  "rope_theta": 1000000.0,23  "router_aux_loss_coef": 0.001,24  "sliding_window": null,25  "tie_word_embeddings": false,26  "torch_dtype": "float16",27  "transformers_version": "4.37.1",28  "use_cache": true,29  "vocab_size": 3200030}31