crumb's picture
Upload MixtralForCausalLM
33925d5
raw
history blame
771 Bytes
{
"_name_or_path": "crumb/mixtral-8x70m-randinit-183m",
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 2048,
"max_position_embeddings": 4096,
"model_type": "mixtral",
"num_attention_heads": 8,
"num_experts_per_tok": 2,
"num_hidden_layers": 6,
"num_key_value_heads": 8,
"num_local_experts": 8,
"output_router_logits": false,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.001,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.36.0.dev0",
"use_cache": true,
"vocab_size": 50277
}