Vladislav Bronzov comments

Results 35 comments of


                                            Vladislav Bronzov

Community contribution: Adding GGUF support for more architectures

@SunMarc I am going to take Qwen2Moe

Community contribution: Adding GGUF support for more architectures

Hi @SunMarc, I take bloom if nobody is working on it

Community contribution: Adding GGUF support for more architectures

Hi @SunMarc! I am going to start working on StableLM model

Community contribution: Adding GGUF support for more architectures

Hi @SunMarc! I suppose GPT2 gguf is not supported yet, if this is a case, I'll take it

Community contribution: Adding GGUF support for more architectures

Hey @SunMarc! I"ll take Starcoder2 as next model

Community contribution: Adding GGUF support for more architectures

Hi @SunMarc! I am going to start working on Mamba

KeyError when loading AutoModelForTokenClassification

Hey, there is no config assignment for this model type. It is needed to add related type and config into mapping. @zucchini-nlp is it ok for you? I could try...

KeyError when loading AutoModelForTokenClassification

@zucchini-nlp Just one thing is weird to me and because of that, I suppose, model loading is failed, is that in config.json of this model "base_model": "xlm-roberta-base". I am not...

`SequenceBiasLogitsProcessor` parameter cannot be specified in the the json config file

Hello! Is anybody working on this bug? If not, then I could try to fix it

`SequenceBiasLogitsProcessor` parameter cannot be specified in the the json config file

@gante @ArthurZucker Hello, I am not quite sure that i understood the idea of this problem and required fix. I tried to reproduce this bug. Yes, we definetely cannot specify...