Pre-submission checklist | 提交前检查

• I have searched existing issues and this hasn't been mentioned before | 我已搜索现有问题，确认此问题尚未被提及
• I have read the project documentation and confirmed this issue doesn't already exist | 我已阅读项目文档并确认此问题尚未存在
• This issue is specific to MemOS and not a general software issue | 该问题是针对 MemOS 的，而不是一般软件问题

Bug Description | 问题描述

There is compatibility issue introduced by chonkie 1.4.0, where the API and parameter changes cause memory initialization to fail with the following error:
SentenceChunker.init() got an unexpected keyword argument 'tokenizer_or_token_counter'

How to Reproduce | 如何重现

1. pip install latest memos package
2. running ollama backend with config like

{
  "llm": {
    "backend": "ollama",
    "config": {
      "model_name_or_path": "llama3.3:70b",
      "temperature": 0.0,
      "remove_think_prefix": true,
      "max_tokens": 8192,
      "api_base": "http://localhost:11434"
    }
  },
  "embedder": {
    "backend": "ollama",
    "config": {
      "model_name_or_path": "nomic-embed-text:latest",
      "api_base": "http://localhost:11434"
    }
  },
  "chunker": {
    "backend": "sentence",
    "config": {
      "tokenizer_or_token_counter": "gpt2",
      "chunk_size": 512,
      "chunk_overlap": 128,
      "min_sentences_per_chunk": 1
    }
  }
}

Notes: even remove the tokenizer_or_token_counter in config it will also cause the error, because in latest code it iwll add this filed.
3. running

Environment | 环境信息

• python 3.12
• memos pip package 1.1.3
• linux

Additional Context | 其他信息

No response

Willingness to Implement | 实现意愿

• I'm willing to implement this myself | 我愿意自己解决
• I would like someone else to implement this | 我希望其他人来解决