cieske comments

Results 6 comments of


                                            cieske

ImportError: Using `bitsandbytes` 8-bit quantization requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes: `pip install -i https://pypi.org/simple/ bitsandbytes`

python 3.10 transformer 4.38.2 bitsandbytes 0.42.0 accelerate 0.27.2 torch 2.0.1+cu117 torch.cuda.is_available() works, nvidia-smi works, import accelerate and bitsandbytes works, but 8-bit quantization doesn't works with same error

Generate nothing from VLLM output

In my case using Mistral Instruct model, input with proper template and setting max_tokens from SamplingParams helps.

calibration dataset

+1 I also wonder if there is any reference for choosing an appropriate calibration dataset.

[MRG] partial_fit implementation in TfidfTransformer

I think this partial_fit function looks really good and looking forward to using this in scikit-learn soon. Thanks for your hard work:)

[MRG] partial_fit implementation in TfidfTransformer

@adrinjalali Sorry for late reply and thanks for reasonable suggestion!

Add support to azure-openai deployed models

> This OpenaiChatCompletionsLM has not been defined and needs to be rewritten？ [@bcarvalho-via](https://github.com/bcarvalho-via) AFAIK, openai api & axure openai api are slightly different, just rewrite above part will make compatiblility...