43 lines
1.0 KiB
JSON
43 lines
1.0 KiB
JSON
{
|
|
"_name_or_path": "/workspace/process/maywell_pivot-moe/source",
|
|
"architectures": [
|
|
"MixtralForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 14336,
|
|
"max_position_embeddings": 32768,
|
|
"model_type": "mixtral",
|
|
"num_attention_heads": 32,
|
|
"num_experts_per_tok": 2,
|
|
"num_hidden_layers": 48,
|
|
"num_key_value_heads": 8,
|
|
"num_local_experts": 4,
|
|
"output_router_logits": false,
|
|
"pad_token_id": 0,
|
|
"pretraining_tp": 1,
|
|
"quantization_config": {
|
|
"bits": 4,
|
|
"group_size": 128,
|
|
"modules_to_not_convert": [
|
|
"gate"
|
|
],
|
|
"quant_method": "awq",
|
|
"version": "gemm",
|
|
"zero_point": true
|
|
},
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_theta": 100000.0,
|
|
"router_aux_loss_coef": 0.001,
|
|
"sliding_window": 8192,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.37.0.dev0",
|
|
"use_cache": true,
|
|
"vocab_size": 32000
|
|
}
|