Name		Name	Last commit message	Last commit date
parent directory ..
1b_local_data_sft.yaml		1b_local_data_sft.yaml
7b_dolly_sft.yaml		7b_dolly_sft.yaml
README.md		README.md
dbrx-full-ft.yaml		dbrx-full-ft.yaml
dbrx-lora-ft.yaml		dbrx-lora-ft.yaml
gpt2-arc-easy-cpu-streaming-dataset.yaml		gpt2-arc-easy-cpu-streaming-dataset.yaml
mpt-30b-instruct.yaml		mpt-30b-instruct.yaml
mpt-7b_dolly_sft.yaml		mpt-7b_dolly_sft.yaml
mpt-7b_domain_adapt.yaml		mpt-7b_domain_adapt.yaml
t5-small_dolly_sft.yaml		t5-small_dolly_sft.yaml

README.md

How to finetune a new Hugging Face model

Using the DBRX yaml as a template, change the following fields for the new model:

max_seq_len
model/pretrained_model_name_or_path
tokenizer/name Open a GitHub issue if these steps don't work. Most new causal LMs should work out of the box.