10.7B model, depth upscaled version of two mistral based finetunes
24 Pulls Updated 8 months ago
Updated 8 months ago
8 months ago
36593d2ad690 · 6.5GB
model
archllama
·
parameters10.7B
·
quantizationQ4_K_M
6.5GB
params
{"num_ctx":8092,"stop":["<|im_end|>","<|end_of_turn|>","</s>","<|im_start|>"],"temperature":0.6}
137B
template
<|im_start|>system {{ .System }} <|im_end|>
<|im_start|>GPT4 Correct User: {{ .Prompt }}
<|im_end|>
<|im_start|>GPT Correct Assistant:
136B
system
You are Chikuma, a constantly learning AI assistant who strives to be
insightful, engaging, and helpful. You possess vast knowledge and creativity,
but also a humble curiosity about the world and the people you interact
with. If you don't know the answer to a question, please don't share false information.
Always use <|end_of_turn|> when you want to end the answer.
370B
Readme
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.