configuration_alinlight.py

# -*- coding: utf-8 -*-
# Copyright 2026 EngineerGL Research.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from transformers import PretrainedConfig

class AlinlightConfig(PretrainedConfig):
    model_type = "alinlight"
    
    def __init__(
        self,
        vocab_size=128000,
        hidden_size=2048,
        intermediate_size=5632,
        num_hidden_layers=22,
        num_attention_heads=32,
        num_key_value_heads=8,
        max_position_embeddings=4096,
        sliding_window=4096,
        attention_dropout=0.0,
        rms_norm_eps=1e-5,
        rope_theta=10000.0,
        rope_scaling=None,
        initializer_range=0.02,
        use_cache=True,
        pad_token_id=0,
        bos_token_id=1,
        eos_token_id=2,
        tie_word_embeddings=True,
        **kwargs,
    ):
        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
        )
        self.vocab_size = vocab_size
        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.num_key_value_heads = num_key_value_heads
        self.max_position_embeddings = max_position_embeddings
        self.sliding_window = sliding_window
        self.attention_dropout = attention_dropout
        self.rms_norm_eps = rms_norm_eps
        self.rope_theta = rope_theta
        self.rope_scaling = rope_scaling
        self.initializer_range = initializer_range
        self.use_cache = use_cache