ifioravanti/
alphamonarch:7b-q8_0

557 1 year ago

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

1 year ago

0fdfd5955be8 · 7.7GB ·

model
llama
·
7.24B
·
Q8_0
params
{ "num_ctx": 8192, "stop": [ "<|im_start|>", "<|im_end|>" ] }
template
{{ if and .First .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}<|im_start|>user {{ .

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

License

cc-by-nc-4.0

References

HuggingFace