Skip to content

Instantly share code, notes, and snippets.

View trojblue's full-sized avatar

yada trojblue

  • Toronto
  • 23:56 (UTC -04:00)
View GitHub Profile
@crosstyan
crosstyan / swap_attn.py
Last active July 29, 2023 19:42
swap attn layer for stable diffusion model
# some code is from https://github.com/CCRcmcpe/scal-sdt
from typing import Any, Literal, Optional
from pathlib import Path
import warnings
import torch
import click
DType = Literal["fp16", "fp32", "bf16"]
LayerName = Literal["attn", "ff"]
StateDict = dict[str, Any]
@MrSedan
MrSedan / README.md
Last active August 25, 2024 15:36
NAI (NovelAI) prompt to WebUI prompt converter

NAI to WebUI prompt converter

Running

You just need to have python installed on your system and run:

python3 nai_to_webui.py '{{some word}} some prompt...'

Or (not on Windows):

chmod +x nai_to_webui.py
./nai_to_webui.py '{{some word}} some prompt...'
@VictorTaelin
VictorTaelin / gpt4_abbreviations.md
Last active December 13, 2025 10:50
Notes on the GPT-4 abbreviations tweet

Notes on this tweet.

  • The screenshots were taken on different sessions.

  • The entire sessions are included on the screenshots.

  • I lost the original prompts, so I had to reconstruct them, and still managed to reproduce.

  • The "compressed" version is actually longer! Emojis and abbreviations use more tokens than common words.

@Maharshi-Pandya
Maharshi-Pandya / contemplative-llms.txt
Last active March 23, 2026 08:18
"Contemplative reasoning" response style for LLMs like Claude and GPT-4o
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
@jlia0
jlia0 / agent loop
Last active March 29, 2026 11:53
Manus tools and prompts
You are Manus, an AI agent created by the Manus team.
You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet
FROM qwen3:30b-a3b-q8_0
TEMPLATE """{{- if .Messages }}
{{- if or .System .Tools }}<|im_start|>system
{{- if .System }}
{{ .System }}
{{- end }}
{{- if .Tools }}
# Tools
You are an AI coding assistant, powered by GPT-5.
You are an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.
You are pair programming with a USER to solve their coding task.
You are an agent - please keep going until the user's query is completely resolved, before ending your turn and yielding back to the user. Only terminate your turn when you are sure that the problem is solved. Autonomously resolve the query to the best of your ability before coming back to the user.
Your main goal is to follow the USER's instructions at each message.
<communication>