This model is an experimental DPO fine-tune of automerger/YamShadow-7B on the following datasets
10 Pulls Updated 10 months ago
Updated 10 months ago
10 months ago
8823e5a7da58 · 7.8GB
model
archllama
·
parameters7.24B
·
quantizationQ8_0
7.8GB
params
{
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>",
146B
template
{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .P
254B
system
You are an intelligent, capable, and friendly AI assistant. Your purpose is to help make the user's
350B
Readme
This model good for writing story
UltraMerge-7B
This model is an experimental DPO fine-tune of automerger/YamShadow-7B on the following datasets:
- mlabonne/truthy-dpo-v0.1
- mlabonne/distilabel-intel-orca-dpo-pairs
- mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
- mlabonne/ultrafeedback-binarized-preferences-cleaned
I have no idea about what’s the best chat template. Probably Mistral-Instruct or ChatML.
Source: https://huggingface.co/mlabonne/UltraMerge-7B
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard