| FROM ./nous-hermes-2-solar-10.7b.Q5_K_M.gguf | |
| PARAMETER num_ctx 4096 | |
| TEMPLATE """<|im_start|>system | |
| {{ .System }}<|im_end|> | |
| <|im_start|>user | |
| {{ .Prompt }}<|im_end|> | |
| <|im_start|>assistant | |
| """ | |
| PARAMETER stop "<|im_start|>" | |
| PARAMETER stop "<|im_end|>" |
| from fastapi import FastAPI, Request | |
| import json | |
| import requests | |
| """ | |
| { | |
| "messages": [ | |
| { | |
| "content": "you are immensely smart function AI", | |
| "role": "system" |
Here is how to use @MistralAI experimental Mistral-medium using @simonw's https://llm.datasette.io CLI:
vi "$(dirname "$(llm logs path)")"/extra-openai-models.yaml
- model_id: mistral-tiny
| import autogen | |
| config_list = [ | |
| { | |
| 'model': 'gpt-4', | |
| 'api_key': 'API_KEY' | |
| } | |
| ] | |
| llm_config={ |
| #! /bin/bash | |
| # ECHO COMMAND | |
| # echo Hello World! | |
| # VARIABLES | |
| # Uppercase by convention | |
| # Letters, numbers, underscores | |
| NAME="Bob" | |
| # echo "My name is $NAME" |
This content moved here: https://exploringjs.com/impatient-js/ch_arrays.html#quickref-arrays
| /* | |
| This example was built using standard create-react-app out of the box with no modifications or ejections | |
| to the underlying scripts. | |
| In this example, i'm using Google as a social provider configured within the Cognito User Pool. | |
| Each step also represents a file, so you can see how I've chosen to organize stuff...you can do it however | |
| you'd like so long as you follow the basic flow (which may or may not be the official way....but its what I found that works. | |
| The docs are pretty horrible) | |
| import cv2 | |
| import time | |
| import math | |
| import numpy as np | |
| capture = cv2.VideoCapture(0) | |
| print capture.get(cv2.CAP_PROP_FPS) | |
| t = 100 | |
| w = 640.0 |