# Copyright 2026 The TensorMind team. All rights reserved.
#
# 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.
"""TensorMind model configuration"""

try:
    from transformers.configuration_utils import PreTrainedConfig
    from transformers.modeling_rope_utils import RopeParameters
except ImportError:
    from transformers.configuration_utils import PretrainedConfig as PreTrainedConfig
    RopeParameters = None


class TensorMindConfig(PreTrainedConfig):
    model_type = "tensormind"
    keys_to_ignore_at_inference = ["past_key_values"]
    base_model_tp_plan = {
        "layers.*.self_attn.q_proj": "colwise",
        "layers.*.self_attn.k_proj": "colwise",
        "layers.*.self_attn.v_proj": "colwise",
        "layers.*.self_attn.o_proj": "rowwise",
        "layers.*.mlp.gate_proj": "colwise",
        "layers.*.mlp.up_proj": "colwise",
        "layers.*.mlp.down_proj": "rowwise",
    }
    base_model_pp_plan = {
        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
        "norm": (["hidden_states"], ["hidden_states"]),
    }

    def __init__(
        self,
        vocab_size: int | None = 32768,
        hidden_size: int | None = 1024,
        intermediate_size: int | None = 4096,
        num_hidden_layers: int | None = 32,
        num_attention_heads: int | None = 16,
        num_key_value_heads: int | None = 8,
        hidden_act: str | None = "silu",
        max_position_embeddings: int | None = 32768,
        initializer_range: float | None = 0.02,
        rms_norm_eps: int | None = 1e-6,
        use_cache: bool | None = True,
        tie_word_embeddings: bool | None = True,
        attention_bias: bool | None = False,
        attention_dropout: float | None = 0.0,
        pad_token_id: int | None = None,
        bos_token_id: int | None = None,
        eos_token_id: int | None = None,
        rope_parameters: RopeParameters | dict[str, RopeParameters] | None = {
            "rope_type": "default",
            "rope_theta": 10000.0,
            # YaRN
            # "factor": 4.0,
            # "original_max_position_embeddings": 32768,
            # "attention_factor": 1.0,
            # "beta_fast": 32.0, 
            # "beta_slow": 1.0,
        },
        **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.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.attention_bias = attention_bias
        self.attention_dropout = attention_dropout
        self.rope_parameters = rope_parameters
        self.tie_word_embeddings = tie_word_embeddings
        self.pad_token_id = pad_token_id
        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id

        self._attn_implementation = "sdpa"
        super().__init__(**kwargs)


__all__ = ["TensorMindConfig"]