71 lines
2.3 KiB
Python
71 lines
2.3 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
""" MiniMaxText01 model configuration"""
|
|
|
|
from transformers.configuration_utils import PretrainedConfig
|
|
|
|
|
|
class MiniMaxText01Config(PretrainedConfig):
|
|
model_type = "MiniMaxText01"
|
|
keys_to_ignore_at_inference = ["past_key_values"]
|
|
|
|
def __init__(
|
|
self,
|
|
vocab_size=32000,
|
|
hidden_size=4096,
|
|
intermediate_size=14336,
|
|
num_hidden_layers=32,
|
|
num_attention_heads=32,
|
|
num_key_value_heads=8,
|
|
hidden_act="silu",
|
|
max_position_embeddings=4096 * 32,
|
|
initializer_range=0.02,
|
|
rms_norm_eps=1e-5,
|
|
use_cache=True,
|
|
pad_token_id=None,
|
|
bos_token_id=None,
|
|
eos_token_id=None,
|
|
tie_word_embeddings=False,
|
|
rope_theta=1e6,
|
|
sliding_window=None,
|
|
attention_dropout=0.0,
|
|
num_experts_per_tok=2,
|
|
num_local_experts=8,
|
|
output_router_logits=False,
|
|
router_aux_loss_coef=0.001,
|
|
router_jitter_noise=0.0,
|
|
**kwargs,
|
|
):
|
|
self.vocab_size = vocab_size
|
|
self.max_position_embeddings = max_position_embeddings
|
|
self.hidden_size = hidden_size
|
|
self.intermediate_size = intermediate_size
|
|
self.num_hidden_layers = num_hidden_layers
|
|
self.num_attention_heads = num_attention_heads
|
|
self.sliding_window = sliding_window
|
|
|
|
# for backward compatibility
|
|
if num_key_value_heads is None:
|
|
num_key_value_heads = num_attention_heads
|
|
|
|
self.num_key_value_heads = num_key_value_heads
|
|
self.hidden_act = hidden_act
|
|
self.initializer_range = initializer_range
|
|
self.rms_norm_eps = rms_norm_eps
|
|
self.use_cache = use_cache
|
|
self.rope_theta = rope_theta
|
|
self.attention_dropout = attention_dropout
|
|
|
|
self.num_experts_per_tok = num_experts_per_tok
|
|
self.num_local_experts = num_local_experts
|
|
self.output_router_logits = output_router_logits
|
|
self.router_aux_loss_coef = router_aux_loss_coef
|
|
self.router_jitter_noise = router_jitter_noise
|
|
super().__init__(
|
|
pad_token_id=pad_token_id,
|
|
bos_token_id=bos_token_id,
|
|
eos_token_id=eos_token_id,
|
|
tie_word_embeddings=tie_word_embeddings,
|
|
**kwargs,
|
|
)
|