NousResearch/Hermes-2-Pro-Mistral-7B fine-tuned on mlabonne/orpo-dpo-mix-40k dataset
23 Pulls Updated 5 months ago
Updated 5 months ago
5 months ago
e092dd53229e · 14GB
model
archllama
·
parameters7.24B
·
quantizationF16
14GB
params
{"temperature":0.1}
20B
Readme
Test of fine tuning with mlabonne/orpo-dpo-mix-40k dataset on NousResearch/Hermes-2-Pro-Mistral-7B model