Search Results for "llama-2-7b" - Page 4
Sort By:
Showing 3057 open source projects for "llama-2-7b"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
1
LongWriter
Unleashing 10,000+ Word Generation from Long Context LLMs
LongWriter is an open-source framework and set of large language models designed to enable ultra-long text generation that can exceed 10,000 words while maintaining coherence and structure. Traditional large language models can process large inputs but often struggle to generate long outputs due to limitations in training data and alignment strategies. LongWriter addresses this challenge by introducing a specialized dataset and training approach that encourages models to produce longer... -
2
Chat with LLMs Everywhere
Run PyTorch LLMs locally on servers, desktop and mobile
...TorchChat supports running models through Python interfaces as well as integrating them directly into native applications written in languages such as C or C++. The project also demonstrates how modern LLMs like LLaMA-style models can be deployed locally while maintaining good performance across different hardware platforms. -
3
Elia
Terminal-based LLM chat tool with multi-model and local support
...It runs entirely in the command line, offering a keyboard-driven experience that reduces the need for switching between apps. Users can chat with both proprietary models like ChatGPT and Claude, as well as local models such as Llama 3, Mistral, and Gemma. Elia stores conversations in a local SQLite database, making it easy to revisit past interactions. It supports flexible usage with inline and full-screen chat modes, along with simple configuration through a single file. Installation is straightforward via pipx, and users can customize themes, system prompts, and model settings. ... -
4
Cosmos-RL
Cosmos-RL is a flexible and scalable Reinforcement Learning framework
...The framework supports multiple parallelism strategies, including tensor, pipeline, and data parallelism, allowing it to leverage large GPU clusters effectively. It is built with compatibility in mind, supporting popular model families such as LLaMA, Qwen, and diffusion-based world models, as well as integration with Hugging Face ecosystems. cosmos-rl also includes support for advanced RL algorithms, low-precision training, and fault-tolerant execution, making it suitable for large-scale production workloads. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
JAX Toolbox
Public CI, Docker images for popular JAX libraries
...It provides prebuilt Docker images, continuous integration pipelines, and optimized example implementations that help developers quickly set up and run JAX workloads without complex configuration. The project supports popular JAX-based frameworks and models, including architectures used for large-scale pretraining such as GPT and LLaMA variants. By offering curated environments and tested configurations, it reduces compatibility issues and accelerates development workflows for both research and production. The repository also includes performance-optimized examples that demonstrate best practices for leveraging NVIDIA hardware effectively. Its integration with container-based workflows makes it suitable for reproducible experiments and scalable deployments across different environments. -
6
EmoLLM
Pre & Post-training & Dataset & Evaluation & Depoly & RAG
...Its repository includes multiple model variants and training configurations spanning several underlying model families, including InternLM, Qwen, DeepSeek, Mixtral, LLaMA, and others, which shows that the initiative is structured as a broad ecosystem rather than a single release. The project also covers more than just model weights, with material for datasets, fine-tuning, evaluation, deployment, demos, RAG, and related subprojects such as its psychological digital assistant work. -
7
OpenCore Legacy Patcher
Experience macOS just like before
A Python-based project revolving around Acidanthera's OpenCorePkg and Lilu for both running and unlocking features in macOS on supported and unsupported Macs. Our project's main goal is to breathe new life into Macs no longer supported by Apple, allowing for the installation and usage of macOS Big Sur and newer on machines as old as 2007. -
8
LLM-Pruner
On the Structural Pruning of Large Language Models
LLM-Pruner is an open-source framework designed to compress large language models through structured pruning techniques while maintaining their general capabilities. Large language models often require enormous computational resources, making them expensive to deploy and inefficient for many practical applications. LLM-Pruner addresses this issue by identifying and removing non-essential components within transformer architectures, such as redundant attention heads or feed-forward... -
9
TAME LLM
Traditional Mandarin LLMs for Taiwan
TAME LLM is an open-source initiative focused on building and releasing large language models optimized for Traditional Mandarin and the linguistic context of Taiwan. The project includes models such as Llama-3-Taiwan-70B, which are fine-tuned versions of large transformer architectures trained on extensive corpora containing both Traditional Mandarin and English text. These models are designed to support applications such as conversational AI, knowledge retrieval, and domain-specific reasoning in fields like manufacturing, law, healthcare, and electronics. ... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
Intel LLM Library for PyTorch
Accelerate local LLM inference and finetuning
...The framework provides hardware-aware optimizations and low-precision computation techniques that significantly improve the performance of large language models while reducing memory consumption. IPEX-LLM supports a wide range of popular models, including architectures such as LLaMA, Mistral, Qwen, and other transformer-based systems. The library can integrate with common AI frameworks and serving tools such as Hugging Face Transformers, LangChain, and vLLM, allowing developers to incorporate optimized inference into existing pipelines. -
11
Penzai
A JAX research toolkit to build, edit, & visualize neural networks
Penzai, developed by Google DeepMind, is a JAX-based library for representing, visualizing, and manipulating neural network models as functional pytree data structures. It is designed to make machine learning research more interpretable and interactive, particularly for tasks like model surgery, ablation studies, architecture debugging, and interpretability research. Unlike conventional neural network libraries, Penzai exposes the full internal structure of models, enabling fine-grained... -
12
Synthetic Data Kit
Tool for generating high quality Synthetic datasets
Synthetic Data Kit is a CLI-centric toolkit for generating high-quality synthetic datasets to fine-tune Llama models, with an emphasis on producing reasoning traces and QA pairs that line up with modern instruction-tuning formats. It ships an opinionated, modular workflow that covers ingesting heterogeneous sources (documents, transcripts), prompting models to create labeled examples, and exporting to fine-tuning schemas with minimal glue code. -
13
Video2X
A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K
A lossless video/GIF/image upscale achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley 2, 2018. The latest Windows update is built based on version 4.8.1. GUI is not available for 5.0.0 yet, but is already under development. Go to the GUI page to see the basic usage of the GUI. Try the mirror if you can't download releases directly from GitHub. You can use Video2X on Google Colab for free if you don't have a powerful GPU of your own. -
14
CogVLM2
GPT4V-level open-source multi-modal model based on Llama3-8B
CogVLM2 is the second generation of the CogVLM vision-language model series, developed by ZhipuAI and released in 2024. Built on Meta-Llama-3-8B-Instruct, CogVLM2 significantly improves over its predecessor by providing stronger performance across multimodal benchmarks such as TextVQA, DocVQA, and ChartQA, while introducing extended context length support of up to 8K tokens and high-resolution image input up to 1344×1344. The series includes models for both image understanding and video understanding, with CogVLM2-Video supporting up to 1-minute videos by analyzing keyframes. ... -
15
NetherSX2
Continuation of NetherSX2 based on AetherSX2 4248
NetherSX2-patch is a community-driven continuation and enhancement of the NetherSX2 Android PlayStation 2 emulator, itself a modded fork of the open-source AetherSX2 project originally based on PCSX2. It focuses on providing a more complete and feature-rich experience by applying patches to the upstream emulator build and removing ad-related bloat, fixing notification issues, and exposing many internal settings so users have finer control over performance and compatibility on mobile devices. ... -
16
Real-ESRGAN GUI
Cross-platform GUI for image upscaler Real-ESRGAN
...According to actual measurements, arm64the single-architecture performance is better than universal2the dual- architecture Mac on the Apple chip, so Apple chip users are advised to pack arm64single-architecture applications by themselves. Real-ESRGAN can only enlarge the input image with a fixed 2-4x magnification (related to the selected model). This functionality is achieved by downsampling using a conventional scaling algorithm after multiple calls to Real-ESRGAN. Split each frame of the GIF and record the duration, zoom in one by one and then merge. Drag an image file or directory to any position in the window, and its path can be automatically set as the input. -
17
Certbot
Get free HTTPS certificates forever from Let's Encrypt
Certbot is a fully-featured, easy-to-use, extensible client for the Let's Encrypt CA. It fetches a digital certificate from Let’s Encrypt, an open certificate authority launched by the EFF, Mozilla, and others. This certificate then lets browsers verify the identity of web servers and ensures secure communication over the Web. Obtaining and maintaining a certificate is usually such a hassle, but with Certbot and Let’s Encrypt it becomes automated and hassle-free. With just a few simple... -
18
MESHROOM
3D reconstruction software
...Photography is the projection of a 3D scene onto a 2D plane, losing depth information. The goal of photogrammetry is to reverse this process. The dense modeling of the scene is the result yielded by chaining two computer vision-based pipelines, “Structure-from-Motion” (SfM) and “Multi View Stereo” (MVS). Fusion of Multi-bracketing LDR images into HDR. Alignment of panorama images. Support for fisheye optics. Automatically estimate fisheye circle or manually edit it. Take advantage of motorized-head file. Easy to integrate in your Renderfarm System. ... -
19
mitmproxy
A free and open source interactive HTTPS proxy
mitmproxy is an open source, interactive SSL/TLS-capable intercepting HTTP proxy, with a console interface fit for HTTP/1, HTTP/2, and WebSockets. It's the ideal tool for penetration testers and software developers, able to debug, test, and make privacy measurements. It can intercept, inspect, modify and replay web traffic, and can even prettify and decode a variety of message types. Its web-based interface mitmweb gives you a similar experience as Chrome's DevTools, with the addition of features like request interception and replay. ... -
20
gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models
gpt-oss is OpenAI’s open-weight family of large language models designed for powerful reasoning, agentic workflows, and versatile developer use cases. The series includes two main models: gpt-oss-120b, a 117-billion parameter model optimized for general-purpose, high-reasoning tasks that can run on a single H100 GPU, and gpt-oss-20b, a lighter 21-billion parameter model ideal for low-latency or specialized applications on smaller hardware. Both models use a native MXFP4 quantization for efficient memory use and support OpenAI’s Harmony response format, enabling transparent full chain-of-thought reasoning and advanced tool integrations such as function calling, browsing, and Python code execution. ... -
21
SAM 3
Code for running inference and finetuning with SAM 3 model
...It accepts both text prompts (open-vocabulary concepts like “red car” or “goalkeeper in white”) and visual prompts (points, boxes, masks) and returns high-quality masks, boxes, and scores for the requested concepts. Compared with SAM 2, SAM 3 introduces the ability to exhaustively segment all instances of an open-vocabulary concept specified by a short phrase or exemplars, scaling to a vastly larger set of categories than traditional closed-set models. This capability is grounded in a new data engine that automatically annotated over four million unique concepts, producing a massive open-vocabulary segmentation dataset and enabling the model to achieve 75–80% of human performance on the SA-CO benchmark, which itself spans 270K unique concepts. -
22
Mobile Verification Toolkit
Helps with conducting forensics of mobile devices
Mobile Verification Toolkit (MVT) is a collection of utilities to simplify and automate the process of gathering forensic traces helpful to identify a potential compromise of Android and iOS devices. It has been developed and released by the Amnesty International Security Lab in July 2021 in the context of the Pegasus project along with a technical forensic methodology and forensic evidence. MVT is a forensic research tool intended for technologists and investigators. Using it requires... -
23
rnet
Python HTTP client with TLS and HTTP/2 fingerprint emulation support
...It provides a flexible API for making HTTP requests while supporting both asynchronous and blocking workflows, allowing it to integrate easily into different Python applications and runtimes. rnet focuses on low-level protocol customization, giving users fine-grained control over TLS and HTTP/2 configuration in order to emulate specific browser behaviors. This includes support for TLS fingerprinting techniques such as JA3 and JA4 as well as detailed HTTP/2 settings, enabling more accurate simulation of real client network traffic. It is powered by the underlying wreq engine and is built with performance and modularity in mind. rnet also supports advanced networking capabilities such as proxy rotation, connection pooling, and streaming transfers, which make it suitable for automation, scraping, and high-performance network. -
24
alphageometry
AI-driven neuro-symbolic solver for high-school geometry problems
AlphaGeometry, developed by Google DeepMind, is a theorem-proving system that combines symbolic reasoning with deep learning to solve challenging geometry problems, such as those found in mathematical Olympiads. The repository provides the full implementation of DDAR (Deductive Difference and Abductive Reasoning) and AlphaGeometry, two automated geometry solvers described in the 2024 Nature paper “Solving Olympiad Geometry without Human Demonstrations.” AlphaGeometry integrates a symbolic deduction engine with a transformer-based language model to propose and validate geometric constructions in a stepwise proof process. The DDAR solver focuses purely on rule-based reasoning, while AlphaGeometry enhances this by using a learned model to suggest auxiliary constructions when logical reasoning alone is insufficient. ... -
25
DeepSeek Coder
DeepSeek Coder: Let the Code Write Itself
DeepSeek-Coder is a series of code-specialized language models designed to generate, complete, and infill code (and mixed code + natural language) with high fluency in both English and Chinese. The models are trained from scratch on a massive corpus (~2 trillion tokens), of which about 87% is code and 13% is natural language. This dataset covers project-level code structure (not just line-by-line snippets), using a large context window (e.g. 16K) and a secondary fill-in-the-blank objective to encourage better contextual completions and infilling. Multiple sizes of the model are offered (e.g. 1B, 5.7B, 6.7B, 33B) so users can trade off inference cost vs capability. ...
