Skip to content

Instantly share code, notes, and snippets.

View kwindla's full-sized avatar

Kwindla Hultman Kramer kwindla

26 followers · 0 following
  • United States
View GitHub Profile
@kwindla
kwindla / khk-sonnet-3.5-ice-cream.py
Created June 21, 2024 00:59
Anthropic Claude Sonnet 3.5 inventing new ice cream flavors (Pipecat voice bot)
import asyncio
import aiohttp
import os
import sys
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_response import (
@kwindla
kwindla / khk-llama-3-70B.yml
Last active May 28, 2024 04:30
Llama-3-70B config (works on one GPU no deepspeed; OOMs on multiple GPUs during merge)
base_model: meta-llama/Meta-Llama-3-70B
# deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
# This will be the path used for the data when it is saved to the Volume in the cloud.
- path: data.jsonl
@kwindla
kwindla / khk-llama-3-70B.yml
Created May 27, 2024 22:54
Llama-3-70B config (OOM) - 2
base_model: meta-llama/Meta-Llama-3-70B
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
# This will be the path used for the data when it is saved to the Volume in the cloud.
- path: data.jsonl
@kwindla
kwindla / khk-llama-3-70B.yml
Created May 27, 2024 21:56
Llama-3-70B config (OOM)
base_model: meta-llama/Meta-Llama-3-70B
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
# This will be the path used for the data when it is saved to the Volume in the cloud.
- path: data.jsonl
@kwindla
kwindla / benchmark-llama3-ttfb.py
Created April 19, 2024 19:41
Groq Llama-3 Time To First Byte
import os
import json
import time
import statistics
from groq import Groq
# Set the Groq API key and the number of inferences to run
GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
NUM_INFERENCES = 10
@kwindla
kwindla / friendly-cartoon-robot.py
Created February 25, 2024 00:58
friendly cartoon robot
from datetime import datetime
import asyncio
import aiohttp
import os
import sys
from dailyai.conversation_wrappers import InterruptibleConversationWrapper
from dailyai.queue_frame import StartStreamQueueFrame, TranscriptionQueueFrame, TextQueueFrame, UserStartedSpeakingFrame, UserStoppedSpeakingFrame
from dailyai.services.daily_transport_service import DailyTransportService
from dailyai.services.fireworks_ai_services import FireworksLLMService
@kwindla
kwindla / minimal-cmd-line-asyncio.py
Created February 13, 2024 15:08
asyncio + daily-python + ctrl-c
#
# minimal daily-python command-line client using asyncio
#
import os
import asyncio
import signal
import time
from daily import *
@kwindla
kwindla / print-transcription-events-asyncio.py
Created February 7, 2024 23:28
daily-python transcription events
import os
import asyncio
import signal
import time
from daily import *
class PrintTranscriptApp(EventHandler):
@kwindla
kwindla / motion-screenshare.html
Last active December 9, 2023 16:33
Daily.co sending a motion-optimized screenshare
<html>
<head>
<title>test high bitrate, motion-oriented screenshare</title>
<script src="https://unpkg.com/@daily-co/daily-js"></script>
</head>
<body onload="main()">
<div id="videos"></div>
<script>
async function main() {
@kwindla
kwindla / video2txt.py
Created November 11, 2023 20:56
Extract text from a video file using GPT-4V (very simple demo script)
#!/usr/bin/env python3
import click
import imageio
import imageio_ffmpeg
import io
import base64
from PIL import Image
from openai import OpenAI