MoE-lilkdkdkdns / config.json
jnjj's picture
Upload MixtralForCausalLM
70fdf6a verified
raw
history blame contribute delete
904 Bytes
{
"_name_or_path": "merge/",
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"max_position_embeddings": 131072,
"max_window_layers": 21,
"model_type": "mixtral",
"num_attention_heads": 12,
"num_experts_per_tok": 2,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"num_local_experts": 7,
"output_router_logits": false,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000,
"router_aux_loss_coef": 0.001,
"router_jitter_noise": 0.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.48.2",
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 151936
}