AlphaMonarch-7B is a new DPO merge that retains all the reasoning abilities of the very best merges and significantly improves its conversational abilities.
7b
497 Pulls Updated 10 months ago
Updated 10 months ago
10 months ago
0fdfd5955be8 · 7.7GB
model
archllama
·
parameters7.24B
·
quantizationQ8_0
7.7GB
params
{
"num_ctx": 8192,
"stop": [
"<|im_start|>",
"<|im_end|>"
]
}
74B
template
{{ if and .First .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}<|im_start|>user
{{ .
157B
Readme
AlphaMonarch-7B is a new DPO merge that retains all the reasoning abilities of the very best merges and significantly improves its conversational abilities. Kind of the best of both worlds in a 7B model.
CLI
ollama run ifioravanti/alphamonarch
API
Example:
curl -X POST http://localhost:11434/api/generate -d '{
"model": "ifioravanti/alphamonarch",
"prompt": "Here is a story about llamas eating grass"
}'
Memory requirements
7b models generally require at least 8GB of RAM