V2EX smalltong02
 smalltong02 最近的时间轴更新
smalltong02's repos on GitHub
Python 253 人关注
keras-llm-robot
A web UI Project In order to learn the large language model. This project includes features such as chat, quantization, fine-tuning, prompt engineering templates, and multimodality.
23 人关注
7-Zip-zstd
7-Zip with support for Brotli, Fast-LZMA2, Lizard, LZ4, LZ5 and Zstandard
Rust 5 人关注
keras-rag-chatbot
A project written in the Rust language with the goal of offline load of small LLM Model, specifically RAG (Retrieval Augmented Generation) on mobile devices.
2 人关注
docker-llama2-chat
Play LLaMA2 (official / 中文版 / INT4 / llama2.pp) Together! ONLY 3 STEPS! ( non GPU / 5GB vRAM / 8~14GB vRAM)
Dart 2 人关注
keras-mobile-chatbot
This project uses the Large language model to build a powerful chatbot for mobile devices. You can use voice commands to have it help you use, manage and set up other software on your mobile device.
0 人关注
adaptnlp
An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models.
0 人关注
aifs
Local semantic search. Stupidly simple.
0 人关注
Anima
33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU
0 人关注
autogen
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
0 人关注
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
0 人关注
awesome-chatgpt-prompts
This repo includes ChatGPT prompt curation to use ChatGPT better.
0 人关注
awesome-flutter
An awesome list that curates the best Flutter libraries, tools, tutorials, articles and more.
0 人关注
axolotl
Go ahead and axolotl questions
0 人关注
Bert-VITS2
vits2 backbone with multilingual-bert
0 人关注
blog
Public repo for HF blog posts
0 人关注
byzer-llm
Easy, fast, and cheap pretrain,finetune, serving for everyone
0 人关注
candle
Minimalist ML framework for Rust
0 人关注
cargo-mobile2
Rust on mobile made easy!
0 人关注
chat-ollama
ChatOllama is an open source chatbot based on LLMs. It supports a wide range of language models, and knowledge base management.
0 人关注
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
0 人关注
ChatGLM2-6B
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
0 人关注
ChatGPT-Next-Web
A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。
0 人关注
chatgpt-on-wechat
Wechat robot based on ChatGPT, which using OpenAI api and itchat library. 使用大模型搭建微信聊天机器人,基于 GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/LinkAI,支持个人微信、公众号、企业微信、飞书部署,能处理文本、语音和图片,访问操作系统和互联网,支持基于知识库定制专属机器人。
0 人关注
chatgpt-prompts-chinese
极好的ChatGPT中文提示命令,对标awesome-chatgpt-prompts,命令包含awesome-chatgpt-prompts的中文翻译版(不定期翻译更新和优化,命令为英文命令后加zh),以及部分精选的独创中文命令。
0 人关注
ChatTTS
ChatTTS is a generative speech model for daily dialogue.
0 人关注
chinese-dos-games
Chinese DOS games collections.
0 人关注
codellama
Inference code for CodeLlama models
0 人关注
CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型
0 人关注
ColossalAI
Making large AI models cheaper, faster and more accessible
0 人关注
corenet
CoreNet: A library for training deep neural networks
0 人关注
Cronos-Rootkit
Cronos is Windows 10/11 x64 ring 0 rootkit. Cronos is able to hide processes, protect and elevate them with token manipulation.
0 人关注
DeepEP
DeepEP: an efficient expert-parallel communication library
0 人关注
DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
0 人关注
DeepSeek-V3
0 人关注
Detect-It-Easy
Program for determining types of files for Windows, Linux and MacOS.
0 人关注
dify
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
0 人关注
DualPipe
A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
0 人关注
easy-dataset
A powerful tool for creating fine-tuning datasets for LLM
0 人关注
edge-tts
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
0 人关注
edk2
EDK II
0 人关注
EfiGuard
Disable PatchGuard and DSE at boot time
0 人关注
EPLB
Expert Parallelism Load Balancer
0 人关注
exllamav2
A fast inference library for running LLMs locally on modern consumer-class GPUs
0 人关注
fastapi
FastAPI framework, high performance, easy to learn, fast to code, ready for production
0 人关注
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
0 人关注
FFmpeg
Unofficial FFmpeg with added custom native Visual Studio project build tools. FFmpeg: A complete, cross-platform solution to record, convert and stream audio and video.
0 人关注
flash-attention
Fast and memory-efficient exact attention
0 人关注
FlashMLA
FlashMLA: Efficient MLA Decoding Kernel for Hopper GPUs
0 人关注
flutter-samples
Flutter Samples
0 人关注
FlutterScreens
A collection of Screens and attractive UIs built with Flutter ready to be used in your applications. No external libraries are used. Just download, add to your project and use.
0 人关注
FlutterUnit
【Flutter 集录指南 App】The unity of flutter, The unity of coder.
0 人关注
GDA-android-reversing-Tool
the fastest and most powerful android decompiler(native tool working without Java VM) for the APK, DEX, ODEX, OAT, JAR, AAR, and CLASS file. which supports malicious behavior detection, privacy leaking detection, vulnerability detection, path solving, packer identification, variable tracking, deobfuscation, python&java scripts, device memory extrac
0 人关注
gemini-playground
Deploy a Gemini multimodal chat website in 10 seconds, Severless! 只需准备一个Gemini API Key,10秒即可部署一个Gemini多模态对话的网站。
0 人关注
generative-models
Generative Models by Stability AI
0 人关注
google-cloud-python
Google Cloud Client Library for Python
0 人关注
google-maps-services-python
Python client library for Google Maps API Web Services
0 人关注
gorilla
Gorilla: An API store for LLMs
0 人关注
gpt-crawler
Crawl a site to generate knowledge files to create your own custom GPT from a URL
0 人关注
gptq
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
0 人关注
GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ
0 人关注
hackingtool
ALL IN ONE Hacking Tool For Hackers
0 人关注
hello-world
Hello, GitHub world
0 人关注
hora
efficient approximate nearest neighbor search algorithm collections library written in Rust .
0 人关注
jupyter_client
Jupyter protocol client APIs
C++ 0 人关注
keras-liber-monitor
The highly liberalized and configurable x86/x64 API hooking module for windows.
0 人关注
langchain
Building applications with LLMs through composability
0 人关注
Langchain-Chatchat
Langchain-Chatchat(原Langchain-ChatGLM)基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain
0 人关注
LangChain-Tutorials
0 人关注
lets-chat
Real-time chat app using Firebase, React, TailwindCSS, MongoDB, Node/Express, and Socket.io
0 人关注
LibreHardwareMonitor
Libre Hardware Monitor, home of the fork of Open Hardware Monitor
0 人关注
LightGBM
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
0 人关注
linguist
Language Savant. If your repository's language is being reported incorrectly, send us a pull request!
0 人关注
litellm
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
0 人关注
literary-alpaca2
从词表到微调这就是你所需的一切
0 人关注
llama
Inference code for LLaMA models
0 人关注
llama-cpp-python
Python bindings for llama.cpp
0 人关注
LLaMA-Efficient-Tuning
Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
0 人关注
llama-recipes
Examples and recipes for Llama 2 model
0 人关注
llama.cpp
Port of Facebook's LLaMA model in C/C++
0 人关注
LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
0 人关注
LLMs-In-China
中国大模型
0 人关注
lobe-chat
Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.
0 人关注
localGPT
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
0 人关注
maturin
Build and publish crates with pyo3, rust-cpython and cffi bindings as well as rust binaries as python packages
0 人关注
milvus
A cloud-native vector database, storage for next generation AI applications
0 人关注
mobile-aloha
Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation
0 人关注
MS-DOS
The original sources of MS-DOS 1.25, 2.0, and 4.0 for reference purposes
0 人关注
multimodal-live-api-web-console
A react-based starter app for using the Multimodal Live API over websockets with Gemini
0 人关注
n8n
Free and source-available fair-code licensed workflow automation tool. Easily automate tasks across different services.
0 人关注
ollama
Get up and running with Llama 2, Mistral, Gemma, and other large language models.
0 人关注
open-code-interpreter
An innovative open-source Code Interpreter with (GPT,Gemini,PALM,LLaMa) models.
0 人关注
open-interpreter
OpenAI's Code Interpreter in your terminal, running locally
0 人关注
open-procedures
Tiny, structured coding tutorials that can be searched semantically
0 人关注
Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
0 人关注
openchat
OpenChat: Advancing Open-source Language Models with Imperfect Data
0 人关注
openssl
TLS/SSL and crypto library
0 人关注
OpenVoice
Instant voice cloning by MyShell.
0 人关注
peft
PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
0 人关注
Perplexica
Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI
0 人关注
phidata
Build AI Agents with memory, knowledge and tools.
smalltong02

smalltong02

V2EX 第 673310 号会员,加入于 2024-01-25 23:55:22 +08:00
7 S 86 B
I like windows kernel, llvm, machine learning and deep learning
smalltong02 最近回复了
@pizone

好像 API 不免费了,在这里可以查到价格: https://groq.com/pricing/
Groq 上部署了蒸馏过的 r1 70B 模型,速度超级超级快!也支持免费的 API 调用,可以试试。https://groq.com/
@Aka114514

我已经改了一版捕获摄像头图像帧的方法来处理视频流,这样就没有快门声音了,就是上传发布还需要点时间。你是在国内还是香港使用?可以用 gemini 2.0 进行实时对话吗,我只在加拿大使用过,不知道其它地区使用效果怎么样。
@boshok

为啥呢,小哥哥。
@Aka114514

是的,其实我是调用了 takepicture 功能获取的图像数据,这样省了转换的编码,其实如果获取原始的 pcm 数据流就没这个问题了。我下个版本会进行修复,好像有些国家或地区,在调用拍照的时候必须开启快门声音,为了避免偷拍什么的。请问您的手机是苹果手机还是 ipad? 我的苹果手机没有快门的声音。
请问大家试用过之后有什么反馈吗?

我提供自己的一个测试案例,我复现过 Google 演示中一个非常厉害的功能,我在桌子上放了一个 PC 的头戴式耳机,然后在提问过程中,手机摄像头移动时扫到过这个耳机,在又经过一些问答之后并且摄像头并没有对准桌子和耳机的情况下,我询问是否有看到我的耳机在什么地方,Gemini 2.0 回答耳机在桌子上。
2024-06-19 00:30:00 +08:00
回复了 smalltong02 创建的主题 程序员 对 Qwen 2 模型代理能力的完整测试
@wwvvance
我使用我自己的开源项目支持的 Qwen 函数调用: https://github.com/smalltong02/keras-llm-robot
2024-06-19 00:28:48 +08:00
回复了 smalltong02 创建的主题 程序员 对 Qwen 2 模型代理能力的完整测试
@wwvvance

对于原生支持 Function Call 的模型,比如 OpenAI ,Gemini 和 Kimi 等,我都使用它们提供的接口来进行函数调用。对于不支持函数调用的模型,我使用预置的提示词技术来实现的函数调用功能。Baidu 和 Qwen 的模型原生是支持这个功能的,但是因为需要安装其它的库有点冲突,所以暂时把它们当成不支持来对待的。
2024-06-15 11:34:45 +08:00
回复了 panlatent 创建的主题 分享创造 来推荐推荐自己的开源项目和经验吧
[Keras-llm-robot]( https://github.com/smalltong02/keras-llm-robot) 是一个基于 Langchain 的大语言模型项目,支持各种外部工具的调用,比较偏向于模型的 C 端落地项目,工具包括:代码解释器,知识库,搜索引擎,函数调用和工具箱,可惜同类产品太多,一直不火。
关于     帮助文档     自助推广系统     博客     API     FAQ     Solana     1109 人在线   最高记录 6679       Select Language
创意工作者们的社区
World is powered by solitude
VERSION: 3.9.8.5 26ms UTC 23:49 PVG 07:49 LAX 15:49 JFK 18:49
Do have faith in what you're doing.
ubao msn snddm index pchome yahoo rakuten mypaper meadowduck bidyahoo youbao zxmzxm asda bnvcg cvbfg dfscv mmhjk xxddc yybgb zznbn ccubao uaitu acv GXCV ET GDG YH FG BCVB FJFH CBRE CBC GDG ET54 WRWR RWER WREW WRWER RWER SDG EW SF DSFSF fbbs ubao fhd dfg ewr dg df ewwr ewwr et ruyut utut dfg fgd gdfgt etg dfgt dfgd ert4 gd fgg wr 235 wer3 we vsdf sdf gdf ert xcv sdf rwer hfd dfg cvb rwf afb dfh jgh bmn lgh rty gfds cxv xcv xcs vdas fdf fgd cv sdf tert sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf shasha9178 shasha9178 shasha9178 shasha9178 shasha9178 liflif2 liflif2 liflif2 liflif2 liflif2 liblib3 liblib3 liblib3 liblib3 liblib3 zhazha444 zhazha444 zhazha444 zhazha444 zhazha444 dende5 dende denden denden2 denden21 fenfen9 fenf619 fen619 fenfe9 fe619 sdf sdf sdf sdf sdf zhazh90 zhazh0 zhaa50 zha90 zh590 zho zhoz zhozh zhozho zhozho2 lislis lls95 lili95 lils5 liss9 sdf0ty987 sdft876 sdft9876 sdf09876 sd0t9876 sdf0ty98 sdf0976 sdf0ty986 sdf0ty96 sdf0t76 sdf0876 df0ty98 sf0t876 sd0ty76 sdy76 sdf76 sdf0t76 sdf0ty9 sdf0ty98 sdf0ty987 sdf0ty98 sdf6676 sdf876 sd876 sd876 sdf6 sdf6 sdf9876 sdf0t sdf06 sdf0ty9776 sdf0ty9776 sdf0ty76 sdf8876 sdf0t sd6 sdf06 s688876 sd688 sdf86