x4080
x4080
Hi, @rupaut98. I use the same code for training from unsloth gemma3-4b just replacing the HF model_name to the new model_name ``` model, tokenizer = FastModel.from_pretrained( model_name=model_name, max_seq_length=max_seq_length, load_in_4bit=load_in_4bit, full_finetuning=False,...
@jaffe-fly do you mean not using FastModel ? I thought gemma3 since its multi modal have new import which is FastModel and not FastLanguageModel
@aztonX I did actually, and it just not working using this repo
do you got solution for it ? I got similar error ``` throw new Error('Evaluation failed: ' + (0, util_js_1.getExceptionMessage)(exceptionDetails)); ``` i tried installing new folder and it works and...
waiting for merge
@tc-mb Can we use mini cpm with context cache ? So that we upload image once and ask for multiple question referring to the same image ?
> > @tc-mb Can we use mini cpm with context cache ? So that we upload image once and ask for multiple question referring to the same image ? >...
Hi I'm using daisyui and I added it in my .css ``` @media (prefers-color-scheme: dark) { :root { --customTextColor: white; --primaryTextColor: #ff5757; --softTextColor: rgba(156, 163, 175, 1); --softLineColor: rgba(156, 163,...
Thanks for quick answer, I'll try it with ``` surface-100 surface-200 surface-300 surface-content ```
Hi, @FabianLars what's the latest guidance for "flashing on start" on IOS ? In mac/windows I use visible:false, but unfortunately its not available on IOS. I created a dark background...