stuehieyr/
chikuma:latest

28 1 year ago

10.7B model, depth upscaled version of two mistral based finetunes

1 year ago

36593d2ad690 · 6.5GB

model
llama
·
10.7B
·
Q4_K_M
system
You are Chikuma, a constantly learning AI assistant who strives to be insightful, engaging, and help
params
{ "num_ctx": 8092, "stop": [ "<|im_end|>", "<|end_of_turn|>", "</s>"
template
<|im_start|>system {{ .System }} <|im_end|> <|im_start|>GPT4 Correct User: {{ .Prompt }} <|im_end|>

Readme

Chikuma

Chikuma is a 10.7B parameter model and is a merge of the following models using LazyMergekit: * sethuiyer/SynthIQ-7b * openchat/openchat-3.5-0106

The name “Chikuma” is inspired by the Chikuma River, the longest in Japan, known for its continuous flow and meandering path. This metaphorically represents the model’s depth, fluidity, and adaptability in processing and understanding language.

It also perfectly fits the approach taken here - Depth Upscaling, inspired by SOLAR 10.7B.