Olivier Chafik ochafik

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

How to add an image to a gist

Create a gist if you haven't already.

Clone your gist:

# make sure to replace `<hash>` with your gist's hash
git clone https://gist.github.com/<hash>.git # with https
git clone [email protected]:<hash>.git     # or with ssh

Délit de terrorisme vestimentaire passif: à qui profite la persécution religieuse?

Toute ressemblance avec l'affaire du racolage passif serait purement fortuite.

Ne nous voilons pas la face: en matière de politique publique, ce n'est pas l'intention qui compte, ce sont les résultats.

Eh bien quid justement des intentions en jeu dans l'affaire du burkini, et des résultats probables?

Je vois grosso modo 3 profils majeurs pour nos bien-intentionnés amis anti-burkini:

Angular Dart Check List

The following shows what to watch out for when making Angular Dart applications. For more information about Angular Dart, see angulardart.org.

	#!/usr/bin/env node
	/*
	Gets the file under $OLLAMA_HOME/models/blobs/ for the application/vnd.ollama.image.model key in the manifest
	- Note that metadata of modelId:modelTag is stored under $OLLAMA_HOME/models/manifests/registry.ollama.ai/library/${modelId}/${modelTag}
	- You'll need to get the Jinja template from the original model using llama.cpp's scripts/get_chat_template.py script

	ollama pull qwen2.5-coder:7b
	llama-server -m $( ./get_ollama_gguf.js qwen2.5-coder:7b ) -fa --jinja --chat-template-file <( ./scripts/get_chat_template.py Qwen/Qwen2.5-Coder-7B-Instruct-GGUF tool_use )

	Initially shared here: https://github.com/ggml-org/llama.cpp/pull/9639#issuecomment-2704208342

	Begin by enclosing all thoughts within <thinking> tags, exploring multiple angles and approaches.
	Break down the solution into clear steps within <step> tags. Start with a 20-step budget, requesting more for complex problems if needed.
	Use <count> tags after each step to show the remaining budget. Stop when reaching 0.
	Continuously adjust your reasoning based on intermediate results and reflections, adapting your strategy as you progress.
	Regularly evaluate progress using <reflection> tags. Be critical and honest about your reasoning process.
	Assign a quality score between 0.0 and 1.0 using <reward> tags after each reflection. Use this to guide your approach:

	0.8+: Continue current approach
	0.5-0.7: Consider minor adjustments
	Below 0.5: Seriously consider backtracking and trying a different approach

	#!/usr/bin/env python3

	import subprocess
	import json
	import os
	from pathlib import Path

	import requests
	from requests.compat import urljoin

	#!/usr/bin/env bash

	# --slave /usr/bin/$1 $1 /usr/bin/$1-\${version} \\

	function register_clang_version {
	local version=$1
	local priority=$2

	update-alternatives \
	--install /usr/bin/llvm-config llvm-config /usr/bin/llvm-config-${version} ${priority} \

	// Run with dart:
	// dart async_example.dart
	import 'dart:async';
	f(g) async {
	try {
	final value = await g();
	return 'Result: ' + (value + 1);
	} catch (e) {
	if (e == 'rethrow me') throw e;
	return 'Caught: ' + e;