Vinh Nguyen vinhnx

Prompt structure

Task context
Tone context
Background data, documents, and images
Detailed task description & rules
Examples
Conversation history

Immediate task description or request

Rich Already Answered That!

A list of commonly asked questions, design decisions, reasons why Clojure is the way it is as they were answered directly by Rich (even when from many years ago, those answers are pretty much valid today!). Feel free to point friends and colleagues here next time they ask (again). Answers are pasted verbatim (I've made small adjustments for readibility, but never changed a sentence) from mailing lists, articles, chats.

How to use:

The link in the table of content jumps at the copy of the answer on this page.
The link on the answer itself points back at the original post.

Table of Content

Falsehoods programmers believe about time

This is a compiled list of falsehoods programmers tend to believe about working with time.

Don't re-invent a date time library yourself. If you think you understand everything about time, you're probably doing it wrong.

Falsehoods

There are always 24 hours in a day.
February is always 28 days long.
Any 24-hour period will always begin and end in the same day (or week, or month).

Configuration Explanation for `DeepseekV3ForCausalLM`

Config: https://huggingface.co/deepseek-ai/DeepSeek-V3-Base/blob/main/config.json

This configuration file defines the architecture and hyperparameters for a model named DeepseekV3ForCausalLM, which is a causal language model (LM) based on the DeepseekV3 architecture. Below is an explanation of the key configurations:

Model Architecture

architectures: Specifies the model class, which is DeepseekV3ForCausalLM. This indicates the model is designed for causal language modeling (e.g., text generation).

Which GGUF is right for me? (Opinionated)

Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggml-org/llama.cpp#5962

In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.

llama.cpp feature matrix

See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix

	<!DOCTYPE html>
	<html lang="en">

	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1">
	<title>Vinh Nguyen \| iOS Engineer</title>

	<!-- SEO & sharing meta tags -->
	<meta name="description"

	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	import re
	import torch
	from datasets import load_dataset, Dataset
	from transformers import AutoTokenizer, AutoModelForCausalLM
	from peft import LoraConfig
	from trl import GRPOConfig, GRPOTrainer

	# Ghostty Configuration File
	# Reference: https://ghostty.org/docs/config/reference

	# Theme and Appearance
	custom-shader-animation = false
	bold-is-bright = true
	macos-icon = "chalkboard"
	title = " "
	macos-titlebar-proxy-icon = hidden
	macos-window-shadow = false

	# install DSPy: pip install dspy
	import dspy

	# Ollam is now compatible with OpenAI APIs
	#
	# To get this to work you must include `model_type='chat'` in the `dspy.OpenAI` call.
	# If you do not include this you will get an error.
	#
	# I have also found that `stop='\n\n'` is required to get the model to stop generating text after the ansewr is complete.
	# At least with mistral.

	# vim:fileencoding=utf-8:foldmethod=marker

	# Include theme
	include ./theme.conf

	# ===== Config =====

	font_family Menlo
	font_size 15.0