3 2 weeks ago

This is a GGUF conversion of common-pile/comma-v0.1-2t for use with llama.cpp and Ollama. Comma v0.1-2T is a 7 billion parameter language model trained exclusively on openly licensed and public domain text from the Common Pile v0.1 dataset.

d890061ba826 · 90B
{
"repeat_penalty": 1.1,
"stop": [
"<|end_of_text|>"
],
"temperature": 0.7,
"top_p": 0.9
}