Erich Ocean erichocean

## ltx-video.ipynb

      
              1 file
            
          
              0 forks
            
          
                0 comments
              
            
              1 star
            
          
                hathibelagal-dev
                / ltx-video.ipynb
            
            
              Created
              May 8, 2025 02:01
            
              
                LTX-Video.ipynb
              
          
      Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## dual_math.clj
(ns dual-math
  (:refer-clojure :exclude [+ - * / abs max min sin cos tan asin acos atan exp log pow sqrt])
  (:require [clojure.core :as core]))

;; == Part 1: Dual Number Definition and Helpers ==

(defrecord DualNumber [value deriv])

;; Helper to check if something is a dual number
(defn dual? [x] (instance? DualNumber x))

## o3_pretraining_interface.py
#!/usr/bin/env python3
from flask import Flask, render_template_string

app = Flask(__name__)

@app.route('/')
def dashboard():
    return render_template_string(r'''
<!DOCTYPE html>
<html lang="en">

## grpo_demo.py
# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
"""
citation:

@misc{brown2025grpodemo,
  title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
  author={Brown, William},

## contemplative-llms.txt
You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

## Core Principles

1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference

## sdl3_win32_wmpointer.cpp
// This code does not work as-is. It is a work-in-progress in my application. You need to modify it for your application.

void handle_stylus_event(UINT uMsg, WPARAM wParam)
{
	// Wacom + [DriverSetting: Use Windows Ink] required for these events to happen at all.
	// WinTab mandatory when Windows Ink is disabled in any way.

	if (uMsg == WM_POINTERDEVICECHANGE)
	{
		PRINT_INPUT("DEVICE CHANGE\n");

## scuffed-speculative.py

def generate_speculative(
    model: nn.Module,
    draft_model: nn.Module,
    tokenizer: Union[PreTrainedTokenizer, TokenizerWrapper],
    prompt: str,
    max_tokens: int = 100,
    verbose: bool = False,
    formatter: Optional[Callable] = None,
    **kwargs,

## collect_code.sh
#!/bin/bash

# Check if a GitHub URL is provided as an argument
if [ -z "$1" ]; then
    echo "Usage: $0 <github_url>"
    exit 1
fi

# Store the GitHub URL
GIT_URL="$1"

## gist:533dd0c7d4f3ee8d34a6a905155b72ae
How to quantize 70B model so it will fit on 2x4090 GPUs:

I tried EXL2, AutoAWQ, and SqueezeLLM and they all failed for different reasons (issues opened).

HQQ worked:

I rented a 4x GPU 1TB RAM ($19/hr) instance on runpod with 1024GB container and 1024GB workspace disk space.
I think you only need 2x GPU with 80GB VRAM and 512GB+ system RAM so probably overpaid.

Note you need to fill in the form to get access to the 70B Meta weights.

## prior_likelihood_conflict.r
# prior - likelihood conflict

library(rethinking)

yobs <- 0

mtt <- ulam(
    alist(
        y ~ dstudent(2,mu,1),
        mu ~ dstudent(2,10,1)
	(ns dual-math
	(:refer-clojure :exclude [+ - * / abs max min sin cos tan asin acos atan exp log pow sqrt])
	(:require [clojure.core :as core]))

	;; == Part 1: Dual Number Definition and Helpers ==

	(defrecord DualNumber [value deriv])

	;; Helper to check if something is a dual number
	(defn dual? [x] (instance? DualNumber x))
	#!/usr/bin/env python3
	from flask import Flask, render_template_string

	app = Flask(__name__)

	@app.route('/')
	def dashboard():
	return render_template_string(r'''
	<!DOCTYPE html>
	<html lang="en">
	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	"""
	citation:

	@misc{brown2025grpodemo,
	title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
	author={Brown, William},
	You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

	## Core Principles

	1. EXPLORATION OVER CONCLUSION
	- Never rush to conclusions
	- Keep exploring until a solution emerges naturally from the evidence
	- If uncertain, continue reasoning indefinitely
	- Question every assumption and inference
	// This code does not work as-is. It is a work-in-progress in my application. You need to modify it for your application.

	void handle_stylus_event(UINT uMsg, WPARAM wParam)
	{
	// Wacom + [DriverSetting: Use Windows Ink] required for these events to happen at all.
	// WinTab mandatory when Windows Ink is disabled in any way.

	if (uMsg == WM_POINTERDEVICECHANGE)
	{
	PRINT_INPUT("DEVICE CHANGE\n");

	def generate_speculative(
	model: nn.Module,
	draft_model: nn.Module,
	tokenizer: Union[PreTrainedTokenizer, TokenizerWrapper],
	prompt: str,
	max_tokens: int = 100,
	verbose: bool = False,
	formatter: Optional[Callable] = None,
	**kwargs,
	#!/bin/bash

	# Check if a GitHub URL is provided as an argument
	if [ -z "$1" ]; then
	echo "Usage: $0 <github_url>"
	exit 1
	fi

	# Store the GitHub URL
	GIT_URL="$1"
	How to quantize 70B model so it will fit on 2x4090 GPUs:

	I tried EXL2, AutoAWQ, and SqueezeLLM and they all failed for different reasons (issues opened).

	HQQ worked:

	I rented a 4x GPU 1TB RAM ($19/hr) instance on runpod with 1024GB container and 1024GB workspace disk space.
	I think you only need 2x GPU with 80GB VRAM and 512GB+ system RAM so probably overpaid.

	Note you need to fill in the form to get access to the 70B Meta weights.
	# prior - likelihood conflict

	library(rethinking)

	yobs <- 0

	mtt <- ulam(
	alist(
	y ~ dstudent(2,mu,1),
	mu ~ dstudent(2,10,1)