qnguyen3's picture
Model save
c24ba3b verified
{
"_name_or_path": "qnguyen3/Mixtral-4x400M",
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 7168,
"max_position_embeddings": 4096,
"model_type": "mixtral",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_hidden_layers": 12,
"num_key_value_heads": 8,
"num_local_experts": 4,
"output_router_logits": false,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.02,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.1",
"use_cache": false,
"vocab_size": 38365
}