32 lines
760 B
JSON
32 lines
760 B
JSON
|
|
{
|
||
|
|
"architectures": [
|
||
|
|
"MixtralForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"head_dim": null,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 384,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 768,
|
||
|
|
"max_position_embeddings": 1024,
|
||
|
|
"model_type": "mixtral",
|
||
|
|
"num_attention_heads": 8,
|
||
|
|
"num_experts_per_tok": 2,
|
||
|
|
"num_hidden_layers": 12,
|
||
|
|
"num_key_value_heads": 4,
|
||
|
|
"num_local_experts": 16,
|
||
|
|
"output_router_logits": true,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"router_aux_loss_coef": 0.02,
|
||
|
|
"router_jitter_noise": 0.0,
|
||
|
|
"sliding_window": 1024,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.55.0",
|
||
|
|
"use_cache": false,
|
||
|
|
"vocab_size": 32000
|
||
|
|
}
|