29 lines
711 B
JSON
29 lines
711 B
JSON
{
|
|
"architectures": [
|
|
"MixtralForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 288,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 768,
|
|
"max_position_embeddings": 256,
|
|
"model_type": "mixtral",
|
|
"num_attention_heads": 6,
|
|
"num_experts_per_tok": 2,
|
|
"num_hidden_layers": 6,
|
|
"num_key_value_heads": 6,
|
|
"num_local_experts": 4,
|
|
"output_router_logits": false,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_theta": 1000000.0,
|
|
"router_aux_loss_coef": 0.02,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.36.0.dev0",
|
|
"use_cache": true,
|
|
"vocab_size": 32000
|
|
} |