vanta-research/
apollo-v1-7b:latest

31 2 weeks ago

Apollo V1 7B is a language model designed for advanced reasoning tasks, including logical reasoning, mathematical problem-solving, and research. Built on Mistral 7B-Instruct-v0.3 using LoRA fine-tuning, this model is the first of the Apollo series.

tools
... /
params
c8e2277d96fe · 125B
{
"num_ctx": 32768,
"num_predict": -1,
"repeat_penalty": 1.1,
"stop": [
"[INST]",
"[/INST]"
],
"temperature": 0.7,
"top_k": 40,
"top_p": 0.9
}