NickyDark1

does not have support for mistral, gemma, etc and generate error [BUG] ?

4

model_id = "h2oai/h2o-danube-1.8b-chat"# 

support sft?

3

same title

multiple GPUs

1

multiple GPUs is it possible to train?

phi3 mini model add new token

4

Is it possible to add new token and special tokens to be trained? What would the code be like?

how to fine tune LoRA HQQ?

1

### Feature request how to fine tune LoRA to HQQ? ### Motivation how to fine tune LoRA to HQQ? ### Your contribution how to fine tune LoRA to HQQ?

model: gemma-2b-it-function respond:  my idea: Basically you could have a mini agent who makes the calls to the functions and within them you could have an LLM more qualified...