bnmy6581

``` qa_chain = RetrievalQA.from_chain_type( llm=llm_model, chain_type="stuff", retriever=retriever, #return_source_docummets=True, ) ``` i think `return_source_docummets` is problem

i changed "cuda" -> "cpu" https://github.com/seohyunjun/tortoise-tts recommend using this one

i don't recommend using gpu with torch, because mps doesn't support `fft_r2c`. so you met fft (fast-furier-transform) error. (mps weak calculate complex type) [**current mps issue**] https://github.com/pytorch/pytorch/issues/77764 someday it will...

연산을 위해 dim을 줄여야하는 상황이 계속된다면 CTC의 의존도는 높아질수 밖에 없네요. model이 seq별 dim을 그대로 가져간다면 좀더 정확한 결과가 나올 것 같네요.

@maietta Thank you, it works! if macOS user ``` brew uninstall apidoc npm i -g [email protected] npm i [email protected] ```

저도 같은 현상이라 확인 결과 validation indexing 문제가 있어서 validation shuffle과정에서 데이터가 0개가 되어 문제가 일어났네요. validation쪽 인덱싱 다시 해주고 진행하시면 됩니다!

Thank you, sir, i find request parameter but so difficult. i finally found your pull request. Thank you very much !

> Is anyone else having issues with this release? I am using the latest version but continue to have errors. I believe I read that yfinance, the module that this...

v1.6.5 same situation Excalidraw generate white blank image.svg

``` BitNet/src/ggml-bitnet-lut.cpp:70:131: warning: unused parameter 'dst' [-Wunused-parameter] 70 | size_t ggml_bitnet_mul_mat_get_wsize(const struct ggml_tensor * src0, const struct ggml_tensor * src1, const struct ggml_tensor * dst) { | ^ 45 warnings...