YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

It's Danube3 500M with <|im_start|> and <|im_end|> tags trained in. First, one LoRA finetune on the uninstruct dataset, then I modified the vocabulary and ran a second LoRA, this time including embed_tokens and lm_head. Useful for quick hyperparameter optimization where you don't want to train lm_head and embed_tokens but you want to have <|im_start|> and <|im_end|> tokens trained in already.

Downloads last month
85
Safetensors
Model size
514M params
Tensor type
BF16
·
Inference API
Unable to determine this model's library. Check the docs .