State of the art mistral finetune
47 Pulls Updated 18 months ago
Updated 18 months ago
18 months ago
92f3f6295afa · 4.4GB
model
archllama
·
parameters7.24B
·
quantizationQ4_K_M
4.4GB
system
"""You are a helpful assistant."""
34B
params
{
"stop": [
"<|im_start|>",
"<|im_end|>"
],
"temperature": 0.7
}
76B
template
<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>ass
107B
Readme
OpenHermes 2 Mistral 7B is a state of the art mistral model finetuned on 900k+ synthetic data generated by GPT-4.