|
{ |
|
"_flash_attn_2_enabled": true, |
|
"_name_or_path": "Rakuten/RakutenAI-2.0-8x7B", |
|
"architectures": [ |
|
"MixtralForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"capacity_factor": 0.625, |
|
"eos_token_id": 2, |
|
"eval_capacity_factor": 0.0, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"load_balancing_loss": "switch_topk", |
|
"max_position_embeddings": 32768, |
|
"model_type": "mixtral", |
|
"normalize_router_input": false, |
|
"num_attention_heads": 32, |
|
"num_experts_per_tok": 2, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 8, |
|
"num_local_experts": 8, |
|
"output_router_logits": true, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 10000.0, |
|
"router_aux_loss_coef": 0.01, |
|
"router_gain": 1.0, |
|
"router_jitter_noise": 0.1, |
|
"router_scale": 1.0, |
|
"router_z_loss_coef": 0.0, |
|
"sliding_window": 4096, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.42.4", |
|
"use_attention_mask_in_moe": true, |
|
"use_cache": true, |
|
"use_transformers_inputs": true, |
|
"use_z_loss": true, |
|
"vocab_size": 48000 |
|
} |
|
|