hillhand/
comma-v0.1-2t:latest

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.

2 weeks ago

35d15f3bc0af · 14GB ·

model
llama
·
7B
·
F16
template
{{ .Prompt }}
params
{ "repeat_penalty": 1.1, "stop": [ "<|end_of_text|>" ], "temperature": 0.7,

Readme

No readme