File size: 1,451 Bytes
238fe38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
# Copyright 2026 InstaDeep Ltd and CentraleSupélec
#
# 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 typing import Optional

from transformers import PretrainedConfig


class CellScribeConfig(PretrainedConfig):
    """``scfoundation``: hyper-parameters of the scFoundation cell encoder.
    ``llm``: transformers configuration of the language model (Qwen2)."""

    model_type = "cellscribe"

    def __init__(
        self,
        scfoundation: Optional[dict] = None,
        llm: Optional[dict] = None,
        scrnaseq_embedding_dim: int = 3072,
        max_new_tokens: int = 80,
        **kwargs,
    ) -> None:
        self.scfoundation = scfoundation or {}
        self.llm = llm or {}
        self.scrnaseq_embedding_dim = scrnaseq_embedding_dim
        self.max_new_tokens = max_new_tokens
        kwargs.setdefault(
            "tie_word_embeddings", self.llm.get("tie_word_embeddings", True)
        )
        super().__init__(**kwargs)