Skip to content

Instantly share code, notes, and snippets.

View fullstackwebdev's full-sized avatar

fullstack fullstackwebdev

  • FSWD
  • 00:58 (UTC -07:00)
View GitHub Profile
@transitive-bullshit
transitive-bullshit / claude-code-prompts.js
Last active April 25, 2025 19:52
Unminified prompts and tool definitions for Claude Code
// Claude Code is a Beta product per Anthropic's Commercial Terms of Service.
// By using Claude Code, you agree that all code acceptance or rejection decisions you make,
// and the associated conversations in context, constitute Feedback under Anthropic's Commercial Terms,
// and may be used to improve Anthropic's products, including training models.
// You are responsible for reviewing any code suggestions before use.
// (c) Anthropic PBC. All rights reserved. Use is subject to Anthropic's Commercial Terms of Service (https://www.anthropic.com/legal/commercial-terms).
// Version: 0.2.9
@hanxiao
hanxiao / testRegex.js
Last active April 22, 2025 02:43
Regex for chunking by using all semantic cues
// Updated: Aug. 20, 2024
// Run: node testRegex.js whatever.txt
// Live demo: https://jina.ai/tokenizer
// LICENSE: Apache-2.0 (https://www.apache.org/licenses/LICENSE-2.0)
// COPYRIGHT: Jina AI
const fs = require('fs');
const util = require('util');
// Define variables for magic numbers
const MAX_HEADING_LENGTH = 7;
@VictorTaelin
VictorTaelin / fast_dps_add_carry.md
Last active April 26, 2025 15:08
Fast Discrete Program Search with HVM Superpositions (SUP nodes) - finding ADD-CARRY

HOC's Fast Discrete Program Search (DPS)

HOC will soon (EOY?) launch an API for our DPS solution. The interface will be simple:

  • You give us a set of examples (input/output pairs)

  • We'll give you a (Python?) function that models it

And that's it. It will be an universal function finder.

@migtissera
migtissera / mistral-7B-qlora.yaml
Last active March 30, 2024 22:08
Axolotl config to train a Mistral-7B base using QLoRA on 24GB GPU
base_model: /path/to/Mistral-7B-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
is_llama_derived_model: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets: