mixtral_2x300m_dummy / config.json
OsakanaTeishoku's picture
Upload config.json
c22cfe3 verified
raw
history blame contribute delete
740 Bytes
{
"_name_or_path": "None",
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2400,
"max_position_embeddings": 131072,
"model_type": "mixtral",
"num_attention_heads": 16,
"num_experts_per_tok": 1,
"num_hidden_layers": 24,
"num_key_value_heads": 8,
"num_local_experts": 2,
"output_router_logits": true,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"router_aux_loss_coef": 0.001,
"sliding_window": 1024,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.39.1",
"use_cache": true,
"vocab_size": 50257
}