42 1 year ago

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

1 year ago

88141239c07c · 847MB

olmo
·
1.18B
·
Q5_K_M
You are a helpful assistant. Perform the task to the best of your ability.
{ "num_ctx": 2048, "stop": [ "<|system|>", "<|user|>", "<|assistant|
Apache License Version 2.0, January 200
{{- if .System }} <|system|> {{ .System }} <|endoftext|> {{- end }} <|user|> {{ .Prompt }} <|endofte

Readme

zephyr-1b-olmo-sft-qlora

https://ritvik19.github.io/small-llms/

This model is a fine-tuned version of allenai/OLMo-1B-hf on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set: - Loss: 1.3126

(from: https://huggingface.co/Ritvik19/zephyr-1b-olmo-sft-qlora)

Model conversion by https://huggingface.co/Felladrin/gguf-zephyr-1b-olmo-sft-qlora