Mengbing Wang

Python 版本的，自定义带删除功能的堆。直接在heapq上包了一层，更好的办法是参考labuladong堆的实现文章里的方法。 startMap 和 endMap定义稍有不同，搞的有点复杂。 ```py class MyHeap: def __init__(self): self.data = [] self.deleted = set() def top(self): self.lazy_deletion() return self.data[0] def pop(self): self.lazy_deletion() return heapq.heappop(self.data) def delete(self, key): self.deleted.add(key)...

想到一个类似的题，力扣679题 24点游戏，还是非常经典的dfs。

发现弹栈的时机有两种，本文和力扣官方解答分别用到了这两种。 调用者弹栈 ``` class Solution: def dfs(self, node, graph, path, endnote): path += [node] if path and path[-1] == endnote: self.ans.append(path[:]) return for nodeNext in graph[node]: self.dfs(nodeNext, graph, path, endnote)...

官方题解的贪心没有排序，是O(time+n)的复杂度。没有这里的答案好理解。

.take

Hi, The PR is created: [23522](https://github.com/openvinotoolkit/openvino/pull/23522)

Not sure why the CI failed, it could run locally: ``` convert_tokenizer ./Baichuan2-7B-Chat/pytorch/dldt/FP16/ --output ./Baichuan2-7B-Chat/pytorch/dldt/FP16/ --with-detokenizer --trust-remote-code Loading Huggingface Tokenizer... Converting Huggingface Tokenizer to OpenVINO... Saved OpenVINO Tokenizer: Baichuan2-7B-Chat/pytorch/dldt/FP16/openvino_tokenizer.xml, Baichuan2-7B-Chat/pytorch/dldt/FP16/openvino_tokenizer.bin...

> Not sure why the CI failed, it could run locally: > > ``` > convert_tokenizer ./Baichuan2-7B-Chat/pytorch/dldt/FP16/ --output ./Baichuan2-7B-Chat/pytorch/dldt/FP16/ --with-detokenizer --trust-remote-code > Loading Huggingface Tokenizer... > Converting Huggingface Tokenizer to...

Hello @pavel-esir , I've added pip install bitsandbytes step before running this model. Could we try CI again to see if this time it works? Thanks a lot!

I've checked the new error in CI, this is expected. We need to wait for the change to intel-optimum to be merged. [https://github.com/openvinotoolkit/openvino.genai/issues/273#issuecomment-2017885879](https://github.com/openvinotoolkit/openvino.genai/issues/273#issuecomment-2017885879)