MY-LLM

MY-LLM

connecting

model

my-llm v1.0

params

—

arch

decoder

quant

int8

device

cpu

parameters

temperature

0.80

top_k

40

max_tokens

256

endpoint

POST

/chat

POST

/generate

last run

time

—

tok/s

—

tokens

—

port

3001

⬡

Ready to inference

model loaded · awaiting prompt

transformers

story

code

future of AI

haiku

>

↵ send · shift+↵ newline

0