LukeMauldin

#!/usr/bin/env python3.12
"""
LiteLLM to Aider Configuration Generator

This tool generates configuration files that allow Aider to work seamlessly with LiteLLM models.
It can generate both model settings (YAML) and model metadata (JSON) files.

The generated configurations correctly handle model names in the format "litellm/provider/model" 
by using Aider's extra_params feature to pass the proper model name format to LiteLLM.

zackangelo

<|begin_of_text|><|start_header_id|>system<|end_header_id|>Environment: ipython
Cutting Knowledge Date: December 2023
Today Date: 13 Dec 2024


# Tool Instructions
You may optionally call functions that you have been given access to. You DO NOT have 
to call a function if you do not require it. ONLY call functions if you need them. Do NOT call
functions that you have not been given access to.

michabbb

<?php

namespace App\Services\google;

use Exception;
use Illuminate\Http\Client\ConnectionException;
use Illuminate\Support\Facades\Http;

class Gemini
{

cugu

Webhooks for PocketBase

A simple webhook plugin for PocketBase.

Adds a new collection "webhooks" to the admin interface, to manage webhooks.

Example

The webhook record in the following example send create, update, and delete events in the tickets collection to http://localhost:8080/webhook.

oplanre

<?php
class Pipeline {
    public function __construct(
        private mixed $data
    ) {}
    public function pipe(callable ...$callbacks): static {
        foreach ($callbacks as $callback) {
            $this->data = $callback($this->data);
        }
        return $this;

roychri

Stream Ollama (openai) chat completion API on CLI with HTTPie and jq

Explanation

This command sends a request to the Chat Completion API to generate high-level documentation for the file @src/arch.js. The API is configured to use the llama3-gradient model and to respond in Markdown format.

The messages array contains two elements:

• The first element is a system message that provides the prompt for the API.
• The second element is a user message that specifies the file for which to generate documentation.

e-p-armstrong

# Machine Intelligence Made to Impersonate Characteristics: MIMIC

# NOTE run this $ conda install -c conda-forge mpi4py mpich to get mpi working
# accelerate launch --use_deepspeed -m axolotl.cli.train ./config_name_here
base_model: alpindale/Mistral-7B-v0.2-hf
base_model_config: alpindale/Mistral-7B-v0.2-hf
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

Artefact2

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

garyblankenship

name: Deploy to DigitalOcean

on:
  push:
    branches:
      - main

jobs:
  deploy:
    runs-on: ubuntu-latest

garyblankenship

<?php

/**
 * Graceful cache retrieval and updating macro.
 *
 * First, tries to retrieve the cached value. If not found, uses a grace value.
 * Schedules a background job for updating the cache if grace value is found.
 *
 * @param  string  $key      The cache key to retrieve.
 * @param  int  $ttl      Time to live for the cache, in seconds.