cpfiffer

import outlines
from transformers import AutoTokenizer

model_string = 'deepseek-ai/DeepSeek-R1-Distill-Qwen-7B'
# model_string = 'deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B' # For small machines

model = outlines.models.transformers(
    model_string,
    device='cuda', # also 'cpu', 'mps','auto'
)

philschmid

from typing import Dict, Union
from huggingface_hub import get_safetensors_metadata
import argparse
import sys

# Example: 
# python get_gpu_memory.py Qwen/Qwen2.5-7B-Instruct

# Dictionary mapping dtype strings to their byte sizes
bytes_per_dtype: Dict[str, float] = {

cpfiffer

import outlines
from pydantic import BaseModel
from transformers import AutoTokenizer
from rich import print

model_string = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
model = outlines.models.transformers(model_string)
tokenizer = AutoTokenizer.from_pretrained(model_string)

class Highlights(BaseModel):

dwarkeshsp

#!/usr/bin/env python3
"""
Human quality transcripts from audio files using 
AssemblyAI for transcription and Google's Gemini for enhancement.

Requirements:
- AssemblyAI API key (https://www.assemblyai.com/)
- Google API key (https://aistudio.google.com/)
- Python packages: assemblyai, google-generativeai, pydub

charlesfrye

# Train GPT-2 in five minutes -- for free
#
# ```bash
# pip install modal
# modal setup
# modal run wrapper.py
# ```
#
# Note that the end-to-end latency the first time is more like 25 minutes:
# - five minutes to install Torch (rip)

virattt

andrasbacsai

#!/bin/bash
# Script to update a firewall rule in a Hetzner Firewall with your current IP address.
# Good if you would like to restrict SSH access only for your current IP address (secure).

#################
# WARNING: This script will overwrite all rules in the firewall rules, so make sure you 
# added all the required rules.
# I use a separate firewall rule just for SSH access.
#################

sayakpaul

When loading the LoRA params (that were obtained on a quantized base model) and merging them into the base model, it is recommended to first dequantize the base model, merge the LoRA params into it, and then quantize the model again. This is because merging into 4bit quantized models can lead to some rounding errors. Below, we provide an end-to-end example:

1. First, load the original model and merge the LoRA params into it:

from diffusers import FluxPipeline 
import torch 

ckpt_id = "black-forest-labs/FLUX.1-dev"
pipeline = FluxPipeline.from_pretrained(

kwindla

import asyncio
import base64
import json
import os
import pyaudio
import shutil
import websockets


class AudioStreamer:

karenpayneoregon

var $debugHelper = $debugHelper || {};
$debugHelper = function () {
    var href = "lib/debugger.css";
    var addCss = function () {
        if (styleStyleIsLoaded(href) === true) {
            return;
        }
        const head = document.head;
        const link = document.createElement("link");
        link.type = "text/css";