tomasmcm / zephyr-1b-olmo-sft-qlora

This model is a fine-tuned version of allenai/OLMo-1B-hf on the HuggingFaceH4/ultrachat_200k dataset

14 Pulls Updated 7 weeks ago

... /
template
a3de662650da · 118B
{{- if .System }} <|system|> {{ .System }} <|endoftext|> {{- end }} <|user|> {{ .Prompt }} <|endoftext|> <|assistant|>