This model is a fine-tuned version of allenai/OLMo-1B-hf on the HuggingFaceH4/ultrachat_200k dataset
28 Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
88141239c07c · 847MB
model
archolmo
·
parameters1.18B
·
quantizationQ5_K_M
847MB
system
You are a helpful assistant. Perform the task to the best of your ability.
74B
template
{{- if .System }}
<|system|>
{{ .System }}
<|endoftext|>
{{- end }}
<|user|>
{{ .Prompt }}
<|endofte
118B
params
{"num_ctx":2048,"stop":["\u003c|system|\u003e","\u003c|user|\u003e","\u003c|assistant|\u003e","\u003
140B
license
Apache License
Version 2.0, January 200
11kB
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