Search Results for "alignment" - Page 3
Sort By:
Showing 131 open source projects for "alignment"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
1
GLM-4.6
Agentic, Reasoning, and Coding (ARC) foundation models
GLM-4.6 is the latest iteration of Zhipu AI’s foundation model, delivering significant advancements over GLM-4.5. It introduces an extended 200K token context window, enabling more sophisticated long-context reasoning and agentic workflows. The model achieves superior coding performance, excelling in benchmarks and practical coding assistants such as Claude Code, Cline, Roo Code, and Kilo Code. Its reasoning capabilities have been strengthened, including improved tool usage during inference... -
2
PaLM + RLHF - Pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback)
PaLM-rlhf-pytorch is a PyTorch implementation of Pathways Language Model (PaLM) with Reinforcement Learning from Human Feedback (RLHF). It is designed for fine-tuning large-scale language models with human preference alignment, similar to OpenAI’s approach for training models like ChatGPT. -
3
LongCat-Video
Foundational video generation model with 13.6B parameters
...A coarse-to-fine strategy operates across time and space to produce 720p video at 30 frames per second efficiently. Block Sparse Attention reduces high-resolution inference costs, while multi-reward GRPO training improves visual quality and prompt alignment. The repository includes inference scripts for single- and multi-GPU execution, model-download instructions, and interactive generation examples. It also provides audio-driven Avatar variants for expressive single- or multi-character animation. -
4
canvas-editor
Canvas-based WYSIWYG rich text editor with advanced layout tools
canvas-editor is a browser-based rich text editor that renders content using HTML5 Canvas and SVG instead of traditional DOM-based approaches. It is designed to provide a WYSIWYG editing experience similar to word processors, enabling precise control over layout, rendering, and document structure. canvas-editor supports a wide range of formatting and document features, including text styling, tables, images, and embedded elements, all managed through a structured data model. Its architecture... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
5
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 responses. The system uses an agent-based pipeline called AgentWrite that decomposes large writing tasks into smaller subtasks, allowing the model to produce long documents section by section. ... -
6
nanochat
The best ChatGPT that $100 can buy
...The repository stitches together every stage of the lifecycle: tokenizer training, pretraining a Transformer on a large web corpus, mid-training on dialogue and multiple-choice tasks, supervised fine-tuning, optional reinforcement learning for alignment, and finally efficient inference with caching. Its north star is approachability and speed: you can boot a fresh GPU box and drive the whole pipeline via a single script, producing a usable chat model in hours and a clear markdown report of what happened. The code is written to be read—concise training loops, transparent configs, and minimal wrappers—so you can audit each step, tweak it, and rerun without getting lost in framework indirection. -
7
DataChain
AI-data warehouse to enrich, transform and analyze unstructured data
...Datachain can persist features of Python objects returned by AI models, and enables vectorized analytical operations over them. The typical use cases are data curation, LLM analytics and validation, image segmentation, pose detection, and GenAI alignment. Datachain is especially helpful if batch operations can be optimized – for instance, when synchronous API calls can be parallelized or where an LLM API offers batch processing. -
8
iFixAi
Independent Auditing of AI Agents
iFixAi is an independent auditing toolkit for evaluating whether an AI agent performs the business job it was assigned. Instead of measuring only latency, token use, or prompt-injection resistance, it examines operational behavior, organizational alignment, and task outcomes. A standard run performs 32 inspections across five evaluation pillars and produces an A-to-F grade. Users can configure and launch audits through a guided CLI, explicit command flags, or an agent plugin and skill. The same engine can test hosted providers or a real agent endpoint and can use self-grading, an independent judge, or a multi-judge ensemble. ... -
9
SWIFT LLM
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs
SWIFT LLM is a comprehensive framework developed within the ModelScope ecosystem for training, fine-tuning, evaluating, and deploying large language models and multimodal models. The platform provides a full machine learning pipeline that supports tasks ranging from model pre-training to reinforcement learning alignment techniques. It integrates with popular inference engines such as vLLM and LMDeploy to accelerate deployment and runtime performance. The framework also includes support for many modern training strategies, including preference learning methods and parameter-efficient fine-tuning techniques. ms-swift is designed to work with hundreds of language and multimodal models, providing a unified environment for experimentation and production deployment. -
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
10
Auto-Deep-Research
Your Fully-Automated Personal AI Assistant
...Auto-Deep-Research integrates retrieval from academic and web sources, processes document corpora for relevance and key insights, and organizes outputs into coherent chapters or sections according to research standards. It also embeds validation loops, where intermediate drafts are self-checked for consistency, coverage, and alignment with sound reasoning practices, reducing reliance on raw generation alone. -
11
JavaCV
Java interface to OpenCV, FFmpeg, and more
...JavaCV also comes with hardware accelerated full-screen image display (CanvasFrame and GLCanvasFrame), easy-to-use methods to execute code in parallel on multiple cores (Parallel), user-friendly geometric and color calibration of cameras and projectors (GeometricCalibrator, ProCamGeometricCalibrator, ProCamColorCalibrator), detection and matching of feature points (ObjectFinder), a set of classes that implement direct image alignment of projector-camera systems (mainly GNImageAligner, ProjectiveTransformer, ProjectiveColorTransformer, ProCamTransformer, and ReflectanceInitializer), and more. -
12
Qwen2.5-Math
A series of math-specific large language models of our Qwen2 series
Qwen2.5-Math is a series of mathematics-specialized large language models in the Qwen2 family, released by Alibaba’s QwenLM. It includes base models (1.5B / 7B / 72B parameters), instruction-tuned versions, and a reward model (RM) to improve alignment. Unlike its predecessor Qwen2-Math, Qwen2.5-Math supports both Chain-of-Thought (CoT) reasoning and Tool-Integrated Reasoning (TIR) for solving math problems, and works in both Chinese and English. It is optimized for solving mathematical benchmarks and exams; the 72B-Instruct model achieves state-of-the-art results among open source models on many English and Chinese math tasks. -
13
CUTLASS
CUDA Templates for Linear Algebra Subroutines
CUTLASS is a collection of CUDA C++ template abstractions for implementing high-performance matrix-multiplication (GEMM) and related computations at all levels and scales within CUDA. It incorporates strategies for hierarchical decomposition and data movement similar to those used to implement cuBLAS and cuDNN. CUTLASS decomposes these "moving parts" into reusable, modular software components abstracted by C++ template classes. These thread-wide, warp-wide, block-wide, and device-wide... -
14
Tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
tiktoken is a high-performance, tokenizer library (based on byte-pair encoding, BPE) designed for use with OpenAI’s models. It handles encoding and decoding text to token IDs efficiently, with minimal overhead. Because tokenization is a fundamental step in preparing text for models, tiktoken is optimized for speed, memory, and correctness in model contexts (e.g. matching OpenAI’s internal tokenization). The repo supports multiple encodings (e.g. “cl100k_base”) and lets users switch encoding... -
15
OpenFold
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction
OpenFold carefully reproduces (almost) all of the features of the original open source inference code (v2.0.1). The sole exception is model ensembling, which fared poorly in DeepMind's own ablation testing and is being phased out in future DeepMind experiments. It is omitted here for the sake of reducing clutter. In cases where the Nature paper differs from the source, we always defer to the latter. OpenFold is trainable in full precision, half precision, or bfloat16 with or without... -
16
SimpleHTR
Handwritten Text Recognition (HTR) system implemented with TensorFlow
SimpleHTR is an open-source implementation of a handwriting text recognition system based on deep learning techniques. The project focuses on converting images of handwritten text into machine-readable digital text using neural networks. The system uses a combination of convolutional neural networks and recurrent neural networks to extract visual features and model sequential character patterns in handwriting. It also employs connectionist temporal classification (CTC) to align predicted... -
17
VoxelMorph
Unsupervised Learning for Image Registration
...Once the model has been trained, it can rapidly compute the transformation required to register new image pairs, significantly reducing computational time compared to classical registration algorithms. The framework supports both supervised and unsupervised learning approaches and is commonly used in medical imaging applications such as MRI alignment, anatomical analysis, and longitudinal studies. -
18
Hephaestus
Semi-Structured Agentic Framework. Workflows build themselves
Hephaestus is an open-source semi-structured agentic framework designed to orchestrate multiple AI agents working together on complex tasks. Instead of relying entirely on predefined workflows, the framework allows agents to dynamically create tasks as they explore a problem space. Developers define high-level phases such as analysis, implementation, and testing, while agents generate specific subtasks within those phases. The system continuously monitors agent behavior and task progression,... -
19
CLIP
CLIP, Predict the most relevant text snippet given an image
CLIP (Contrastive Language-Image Pretraining) is a neural model that links images and text in a shared embedding space, allowing zero-shot image classification, similarity search, and multimodal alignment. It was trained on large sets of (image, caption) pairs using a contrastive objective: images and their matching text are pulled together in embedding space, while mismatches are pushed apart. Once trained, you can give it any text labels and ask it to pick which label best matches a given image—even without explicit training for that classification task. ... -
20
Claude Code Video Vision
Give Claude the ability to watch and understand videos
Claude Video Vision is a plugin designed for Claude Code that enables large language models to process and understand video content by transforming it into multimodal inputs the model can reason over. Instead of attempting to directly interpret raw video streams, the system extracts key frames using tools like ffmpeg and processes audio through transcription engines, converting both visual and auditory signals into structured inputs for the model. The result is a perception layer that feeds... -
21
Protenix
A trainable PyTorch reproduction of AlphaFold 3
Protenix is an open-source, trainable PyTorch reimplementation of AlphaFold 3, developed by ByteDance with the goal of democratizing high-accuracy protein structure prediction for computational biology and drug-discovery research. Protenix provides a complete pipeline for turning protein sequences (with optional MSA / sequence alignment) or structural inputs (e.g. PDB/CIF) into full 3D atomic-level structure predictions. It supports both “full” models and lightweight variants such as “Protenix-Mini,” offering a trade-off between speed/compute cost and predictive accuracy — making structure prediction accessible even in resource-constrained environments. The project also includes support for constraints (e.g., specifying residue- or atom-level contact constraints, or pocket constraints) to guide predictions toward biologically or experimentally relevant conformations, which enhances its utility for tasks like modeling complexes, ligands, or antibody–antigen interactions. -
22
DeepSeek V2
Strong, Economical, and Efficient Mixture-of-Experts Language Model
...The V2 model is expected to support more advanced features like better context window handling, more efficient inference, better performance on challenging tasks, and stronger alignment with human feedback. Because DeepSeek is pushing open-weight competition, this V2 iteration is meant to solidify its position in benchmark rankings and in developer adoption. The code in the repository may include description files, support for tool use or plug-in architectures, and artifacts showing fine-tuning or prompt templates. -
23
CyberPPT
A Codex Skill for generating high-density, editable PowerPoints
...Image-generation blueprints guide reconstruction while native text, shapes, tables, charts, and vectors preserve core editability. Multiple quality gates inspect structure, visuals, overflow, spatial alignment, curves, and editable elements. Delivery includes the PPTX, rendered previews, manifests, and QA results, with failed hard gates blocking completion. -
24
ImageBind
ImageBind One Embedding Space to Bind Them All
ImageBind is a multimodal embedding framework that learns a shared representation space across six modalities—images, text, audio, depth, thermal, and IMU (inertial motion) data—without requiring explicit pairwise training for every modality combination. Instead of aligning each pair independently, ImageBind uses image data as the central binding modality, aligning all other modalities to it so they can interoperate zero-shot. This creates a unified embedding space where representations from... -
25
Profile Data
Analyze computation-communication overlap in V3/R1
...The repository contains JSON trace files like train.json, prefill.json, decode.json, and associated assets. Users can load them into tools like Chrome tracing to inspect GPU idle times, overlapping operations, and scheduling alignment. The idea is to bring transparency to internal efficiency tradeoffs, enabling researchers to reproduce, analyze, or improve on DeepSeek’s parallelism strategies. The README explains how trace data corresponds to forward/backward chunks, settings (e.g. EP64, TP1, 4K sequence length), and notes that pipeline communication is excluded for simplicity.
