千橙 iqiancheng

## local_llm_glossary.md

      
              1 file
            
          
              1 fork
            
          
              0 comments
            
          
              16 stars
            
          
                kalomaze
                / local_llm_glossary.md
            
            
              Last active
              April 19, 2024 02:35
            
              
                Local LLM Glossary v2
              
          
    Kalomaze's Local LLM Glossary

Not super comprehensive (yet), but I think having up to date documentation like this should be quite helpful for those out of the loop. Things change all the time in local AI circles, and it can be dizzying to catch up from an outsider's perspective, especially if you are new to the more technical aspects of language models in general (and not just locally hosted LLMs).
Available Models

Llama


A language model series created by Meta. Llama 1 was originally leaked in February 2023; Llama 2 then officially released later that year with openly available model weights & a permissive license. Kicked off the initial wave of open source developments that have been made when it comes to open source language modeling. The Llama series comes in four distinct sizes: 7b, 13b, 34b (only Code Llama was released for Llama 2 34b), and 70b. As of writing, the hotly anticipated Llama 3 has yet to arrive.

Mistral


Mistral AI is a French company that also distributes open weight


## cloud_multifiledownload.user.js
// ==UserScript==
// @name         Bildungscloud Ordner Download
// @version      0.6
// @description  Herunterladen einner kompletten Ordnerstruktur im Dateibereich der Bildungscloud
// @author       Daniel Gaida, N-21
// @match        https://niedersachsen.cloud/files/*
// @match        https://schulcloud-thueringen.de/files/*
// @match        https://brandenburg.cloud/files/*
// @grant        GM_xmlhttpRequest
// @grant        unsafeWindow

## README_hfd.md

      
              2 files
            
          
              25 forks
            
          
              25 comments
            
          
              119 stars
            
          
                padeoe
                / README_hfd.md
            
            
              Last active
              April 23, 2024 06:56
            
              
                CLI-Tool for download Huggingface models and datasets with aria2/wget+git
              
          
    🤗Huggingface Model Downloader

Considering the lack of multi-threaded download support in the official huggingface-cli, and the inadequate error handling in hf_transfer, this command-line tool smartly utilizes wget or aria2 for LFS files and git clone for the rest.
Features


⏯️ Resume from breakpoint: You can re-run it or Ctrl+C anytime.
🚀 Multi-threaded Download: Utilize multiple threads to speed up the download process.
🚫 File Exclusion: Use --exclude or --include to skip or specify files, save time for models with duplicate formats (e.g., *.bin or *.safetensors).
🔐 Auth Support: For gated models that require Huggingface login, use --hf_username and --hf_token to authenticate.
🪞 Mirror Site Support: Set up with HF_ENDPOINT environment variable.


## medium.user.js
// ==UserScript==
// @name        Medium Paywall Bypass
// @namespace   Violentmonkey Scripts
// @run-at      document-start
// @match       *://*.medium.com/*
// @match       *://medium.com/*
// @match       *://*/*
// @grant       none
// @version     2.3
// @inject-into content

## hourly_rainfall_data-2023-09-05|10-00.csv

          
            id
            station
            stationid
            value
            unit
            obstime
            date

            
              0
              流浮山
              RF001
              0
              mm
              2023-09-05T10:00:00+08:00
              2023-09-05

            
              1
              湿地公园
              RF002
              0
              mm
              2023-09-05T10:00:00+08:00
              2023-09-05

            
              2
              水边围
              N12
              0
              mm
              2023-09-05T10:00:00+08:00
              2023-09-05

            
              3
              石岗
              RF003
              0
              mm
              2023-09-05T10:00:00+08:00
              2023-09-05

            
              4
              大美督
              RF004
              0
              mm
              2023-09-05T10:00:00+08:00
              2023-09-05

            
              5
              大埔墟
              RF005
              0
              mm
              2023-09-05T10:00:00+08:00
              2023-09-05

            
              6
              北潭涌
              RF006
              0
              mm
              2023-09-05T10:00:00+08:00
              2023-09-05

            
              7
              滘西洲
              RF007
              0
              mm
              2023-09-05T10:00:00+08:00
              2023-09-05

            
              8
              西贡
              N15
              0
              mm
              2023-09-05T10:00:00+08:00
              2023-09-05

## aliyun_ddns.py
#!/usr/bin/python3
import json
from hashlib import sha1
import hmac
import base64
import datetime
import urllib.parse
from urllib.error import HTTPError
from urllib.request import urlopen
import os

## normcore-llm.md

      
              1 file
            
          
              207 forks
            
          
              38 comments
            
          
              2706 stars
            
          
                veekaybee
                / normcore-llm.md
            
            
              Last active
              April 23, 2024 16:03
            
              
                Normcore LLM Reads
              
          
    Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.
Foundational Concepts


Pre-Transformer Models


## llama2-langchain.py
# this should run on a GPU CoLab notebook
# pip install langchain xformers transformers datasets bitsandbytes accelerate --quiet
# get access to the meta-llama models, accept license, and get a read token

hf_auth = '######'

from langchain.chains import ConversationChain
from langchain.llms import HuggingFacePipeline
from langchain.memory import ConversationSummaryBufferMemory
from langchain.prompts.prompt import PromptTemplate

## ms-edge-tts-api.md

      
              1 file
            
          
              3 forks
            
          
              1 comment
            
          
              19 stars
            
          
                wilinz
                / ms-edge-tts-api.md
            
            
              Last active
              April 2, 2024 09:55
            
              
                微软edge-tts-api（大声朗读协议）
              
          
    edge tts
获取语音列表：
https://speech.platform.bing.com/consumer/speech/synthesize/readaloud/voices/list?trustedclienttoken=6A5AA1D4EAFF4E9FB37E23D68491D6F4
tts接口
wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4&Sec-MS-GEC=C14242292B2241ECB17DD93BD17E481FADED759D70DCE83CA526064D9E90420C&Sec-MS-GEC-Version=1-114.0.1823.67&ConnectionId=373cb9fe3c926de352de8ad4c800b24c HTTP/1.1
Host: speech.platform.bing.com


## gethfd.sh
#!/bin/bash
args=${@:1}  # Capture user-provided arguments

os=$(uname -s | tr '[:upper:]' '[:lower:]')
arch=$(uname -m | tr '[:upper:]' '[:lower:]')
if [ "$arch" = "x86_64" ]; then
    arch="amd64"
fi
	// ==UserScript==
	// @name Bildungscloud Ordner Download
	// @version 0.6
	// @description Herunterladen einner kompletten Ordnerstruktur im Dateibereich der Bildungscloud
	// @author Daniel Gaida, N-21
	// @match https://niedersachsen.cloud/files/*
	// @match https://schulcloud-thueringen.de/files/*
	// @match https://brandenburg.cloud/files/*
	// @grant GM_xmlhttpRequest
	// @grant unsafeWindow
	// ==UserScript==
	// @name Medium Paywall Bypass
	// @namespace Violentmonkey Scripts
	// @run-at document-start
	// @match ://.medium.com/*
	// @match ://medium.com/
	// @match :///*
	// @grant none
	// @version 2.3
	// @inject-into content
id	station	stationid	value	unit	obstime	date
0	流浮山	RF001	0	mm	2023-09-05T10:00:00+08:00	2023-09-05
1	湿地公园	RF002	0	mm	2023-09-05T10:00:00+08:00	2023-09-05
2	水边围	N12	0	mm	2023-09-05T10:00:00+08:00	2023-09-05
3	石岗	RF003	0	mm	2023-09-05T10:00:00+08:00	2023-09-05
4	大美督	RF004	0	mm	2023-09-05T10:00:00+08:00	2023-09-05
5	大埔墟	RF005	0	mm	2023-09-05T10:00:00+08:00	2023-09-05
6	北潭涌	RF006	0	mm	2023-09-05T10:00:00+08:00	2023-09-05
7	滘西洲	RF007	0	mm	2023-09-05T10:00:00+08:00	2023-09-05
8	西贡	N15	0	mm	2023-09-05T10:00:00+08:00	2023-09-05
	#!/usr/bin/python3
	import json
	from hashlib import sha1
	import hmac
	import base64
	import datetime
	import urllib.parse
	from urllib.error import HTTPError
	from urllib.request import urlopen
	import os
	# this should run on a GPU CoLab notebook
	# pip install langchain xformers transformers datasets bitsandbytes accelerate --quiet
	# get access to the meta-llama models, accept license, and get a read token

	hf_auth = '######'

	from langchain.chains import ConversationChain
	from langchain.llms import HuggingFacePipeline
	from langchain.memory import ConversationSummaryBufferMemory
	from langchain.prompts.prompt import PromptTemplate
	#!/bin/bash
	args=${@:1} # Capture user-provided arguments

	os=$(uname -s \| tr '[:upper:]' '[:lower:]')
	arch=$(uname -m \| tr '[:upper:]' '[:lower:]')
	if [ "$arch" = "x86_64" ]; then
	arch="amd64"
	fi