Skip to content

Instantly share code, notes, and snippets.

@fakezeta
fakezeta / qwen3.6_merged_template.jinja
Last active August 21, 2026 09:22
Merged Qwen Multimodal Chat Template from allanchan339 and froggeric
{# =========================
Merged Qwen Multimodal Chat Template from
- https://github.com/allanchan339/vLLM-Qwen3-3.5-3.6-chat-template-fix
- https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates
Features:
- developer role supported (from froggeric)
- <|think_on|> / <|think_off|> toggles (from froggeric)
- Historical reasoning HIDDEN by default (from allanchan339)
- String-form tool arguments parsed as JSON (from allanchan339)
- Non-ASCII escaped in tools/args JSON (from froggeric)
@bartowski1182
bartowski1182 / calibration_datav5.txt
Created January 2, 2026 01:29
Calibration data used for latest imatrix. Includes work from Dampf, Kalomaze, and extra dataset from combined_all_small from edaddario
This file has been truncated, but you can view the full file.
In addition to a significant decrease in hepatic lipid accumulation in the IOE group, which inhibited energy intake by propionate enrichment, hepatic lipids were also significantly reduced in the mice in the IOP group, which was largely enriched with butyrate. Compared with the IOE group, IOP had a stronger regulatory effect on hepatic metabolism and triglyceride metabolism and higher levels of TCA cycle in the host. In addition, butyrate has the ability to promote browning of white adipose tissue (WAT) to brown adipose tissue (BAT).^[@ref39],[@ref40]^ WAT stores energy, whereas BAT uses energy for heating and consequently host energy expenditure increases.^[@ref41],[@ref42]^ However, adipose tissue weight does not change after WAT browning.^[@ref43]^ Therefore, the weight of adipose tissue of mice in the IOP group dominated by butyrate was greater than that of the mice in the IOE group dominated by propionate.
@XFY9326
XFY9326 / gradio-patch.md
Last active January 23, 2026 01:22
Simple patch for gradio to make it work offline

Gradio offline patch

Usage

  1. Put gr_offline.py in your project
  2. Import patch and call patch function before using gradio
  3. Download offline static resources

Example

@bartowski1182
bartowski1182 / qwen_calibration_with_chat.txt
Last active August 30, 2026 00:54
Calibration data used for Qwen3, includes original work from Dampf which built on Kalomaze. Chat tokens added thanks to tofumagnate, additional data generated from Qwen3-30B-A3B Q2_K_L
你好!我是你的新朋友,很高兴认识你。😊
我是个喜欢探索和学习的小机器人,在这里我可以给你提供帮助、解答问题以及分享知识。
虽然我没有真实的身体,请不要介意哦~ 我可以通过文字与您交流,并尽力满足您的需求!
我们可以一起聊聊天?或者您可以问我一些有趣的问题?
不管是什么内容都可以告诉我啦! 🌟
@jlia0
jlia0 / agent loop
Last active September 2, 2026 21:01
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
@tristandruyen
tristandruyen / calibration_data_v5_rc.txt
Last active July 21, 2026 11:51 — forked from bartowski1182/calibration_datav3.txt
Adapted from bartowskis v3, added more languages for sparse moe models like qwen 57B-A14B. Calibration data provided by Dampf, combines his own efforts on top of Kalomaze's. Used for calibrating GGUF imatrix files
===========
; A072257: a(n) = ((6*n-17)*4^n - 1)/3.
; -6,-15,-27,21,597,4437,25941,136533,677205,3233109,15029589,68506965,307582293,1364546901,5995058517,26127717717,113100805461,486762960213,2084490794325,8887718991189,37749899220309,159795689903445,674367131702613,2838206015165781,11915774014084437,49914895870022997,208666782734832981,870695927958295893,3626898899909039445,15084056351939581269,62642068416972019029,259791645704742851925,1076060070966390510933,4451814236455238456661,18397552756179659478357,75951394266153460520277,313250310030353132508501,1290780171984369691743573,5314236415389307413812565,21861408571364544242603349,89863485924687435319825749,369125350255666774676952405,1515187027250335232298407253,6215490613912013463556019541,25480932475290743991673640277,104399609979733736516492809557,427501960233217988265164232021,1749621922190004121857428903253,7156944013788545162616803513685,29261601355268295351215565657429,119581706621529640207855669040469,488468031287944396043396301804885,1994436944359
@bartowski1182
bartowski1182 / calibration_datav3.txt
Last active July 21, 2026 11:47
Calibration data provided by Dampf, combines his own efforts on top of Kalomaze's. Used for calibrating GGUF imatrix files
In addition to a significant decrease in hepatic lipid accumulation in the IOE group, which inhibited energy intake by propionate enrichment, hepatic lipids were also significantly reduced in the mice in the IOP group, which was largely enriched with butyrate. Compared with the IOE group, IOP had a stronger regulatory effect on hepatic metabolism and triglyceride metabolism and higher levels of TCA cycle in the host. In addition, butyrate has the ability to promote browning of white adipose tissue (WAT) to brown adipose tissue (BAT).^[@ref39],[@ref40]^ WAT stores energy, whereas BAT uses energy for heating and consequently host energy expenditure increases.^[@ref41],[@ref42]^ However, adipose tissue weight does not change after WAT browning.^[@ref43]^ Therefore, the weight of adipose tissue of mice in the IOP group dominated by butyrate was greater than that of the mice in the IOE group dominated by propionate.
In conclusion ([Figure [7](#fig7){ref-type="fig"}](#fig7){ref-type="fig"}C), the improvement of ob
@Artefact2
Artefact2 / README.md
Last active August 31, 2026 07:42
GGUF quantizations overview

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

@rutcreate
rutcreate / README.md
Last active April 26, 2026 10:12
Install Python 3.10.x on Ubuntu 20.04

Prerequisite

sudo apt update
sudo apt install software-properties-common -y

Add custom APT repository

@p3jitnath
p3jitnath / opencv-fonts.py
Created June 29, 2020 06:21
Custom OpenCV font
import cv2
import numpy as np
img = np.zeros((100, 300, 3), dtype=np.uint8)
ft = cv2.freetype.createFreeType2()
ft.loadFontData(fontFileName='Ubuntu-R.ttf',
id=0)
ft.putText(img=img,
text='Quick Fox',