Search Results for "ofn-layer-modes"
Sort By:
Showing 30 open source projects for "ofn-layer-modes"
View related business solutions-
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.
-
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
Kimi K2.5
Moonshot's most powerful AI model
...Based on a 1T-parameter Mixture-of-Experts (MoE) architecture with 32B activated parameters, it integrates advanced language reasoning with strong visual understanding. K2.5 supports both “Thinking” and “Instant” modes, enabling either deep step-by-step reasoning or low-latency responses depending on the task. Designed for agentic workflows, it features an Agent Swarm mechanism that decomposes complex problems into coordinated sub-agents executing in parallel. With a 256K context length and MoonViT vision encoder, the model excels across reasoning, coding, long-context comprehension, image, and video benchmarks. ... -
2
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
...The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for immediate responses. They are released under the MIT license, allowing commercial use and secondary development. GLM-4.5 achieves strong performance on 12 industry-standard benchmarks, ranking 3rd overall, while GLM-4.5-Air balances competitive results with greater efficiency. ... -
3
MiniCPM4.1
Achieving 3+ generation speedup on reasoning tasks
MiniCPM4.1 is an enhanced iteration of the MiniCPM4 architecture, introducing improvements in reasoning capabilities, inference speed, and hybrid operation modes that allow dynamic switching between deep reasoning and standard generation. It builds upon the same efficiency-focused philosophy but further optimizes decoding performance, achieving substantial speed gains in reasoning-intensive tasks while maintaining high-quality outputs. One of its key innovations is the hybrid reasoning mode, which allows developers to control whether the model engages in deeper reasoning processes or faster responses depending on the use case. ... -
4
Stable Diffusion WebUI Forge
Stable Diffusion WebUI Forge is a platform on top of Stable Diffusion
...It targets heavy users and researchers who push large models, control nets, and high-resolution pipelines where default settings can become bottlenecks. The fork typically introduces toggles for scheduler behavior, attention implementations, caching, and precision modes to reach better speed or quality on given hardware. It also focuses on stability during long sessions, aiming to reduce out-of-memory failures and provide clearer diagnostics when they occur. The UI surfaces advanced options in a way that remains recognizable to WebUI users, so migration costs are low while gaining experimental features. ... -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
5
Qwen2-Audio
Repo of Qwen2-Audio chat & pretrained large audio language model
...It is trained to accept various audio signal inputs (including speech, sounds, etc.) and perform both voice chat and audio analysis, producing textual responses. It supports two major modes: Voice Chat (interactive voice only input) and Audio Analysis (audio + text instructions), with both base and instruction-tuned models. It is evaluated on many benchmarks (speech recognition, translation, sound classification, emotion, etc.), and offers pretrained models (e.g. 7B) released via ModelScope and Hugging Face. Code & examples provided with Hugging Face transformers, and usage via AutoProcessor, model classes etc. ... -
6
MiMo-V2-Flash
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation
MiMo-V2-Flash is a large Mixture-of-Experts language model designed to deliver strong reasoning, coding, and agentic-task performance while keeping inference fast and cost-efficient. It uses an MoE setup where a very large total parameter count is available, but only a smaller subset is activated per token, which helps balance capability with runtime efficiency. The project positions the model for workflows that require tool use, multi-step planning, and higher throughput, rather than only... -
7
Qwen3
Qwen3 is the large language model series developed by Qwen team
Qwen3 is a cutting-edge large language model (LLM) series developed by the Qwen team at Alibaba Cloud. The latest updated version, Qwen3-235B-A22B-Instruct-2507, features significant improvements in instruction-following, reasoning, knowledge coverage, and long-context understanding up to 256K tokens. It delivers higher quality and more helpful text generation across multiple languages and domains, including mathematics, coding, science, and tool usage. Various quantized versions,... -
8
Antigravity Claude Proxy
Proxy that exposes Antigravity provided claude / gemini models
Antigravity Claude Proxy is a purpose-built proxy server that enables developers to interface with Claude models through a standardized RESTful API, allowing tools and workflows that expect generic HTTP APIs to operate on Anthropic’s Claude without native support. The project acts as a translation layer, receiving web requests in common formats (such as OpenAI-style endpoints) and forwarding them to Anthropic’s API in the required structure, while converting responses back into a familiar shape. This makes it easier to integrate Claude into existing toolchains, scripts, notebooks, or agent frameworks that do not have built-in support for Anthropic’s native SDKs. ... -
9
SAM 3D Objects
Models for object and human mesh reconstruction
SAM 3D Objects is a foundation model that reconstructs full 3D geometry, texture, and spatial layout of objects and scenes from a single image. Given one RGB image and object masks (for example, from the Segment Anything family), it can generate a textured 3D mesh for each object, including pose and approximate scene layout. The model is specifically designed to be robust in real-world images with clutter, occlusions, small objects, and unusual viewpoints, where many earlier 3D-from-image... -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
NVIDIA Isaac GR00T
NVIDIA Isaac GR00T N1.5 is the world's first open foundation model
...The vision-language model remains frozen during both pretraining and finetuning, preserving language understanding and improving generalization. Streamlined MLP connection between vision encoder and LLM with added layer normalization. -
11
Map-Anything
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
...The model flexibly accepts different input combinations (images, intrinsics, poses, sparse or dense depth) and produces a rich set of outputs including per-pixel 3D points, camera intrinsics, camera poses, ray directions, confidence maps, and validity masks. Its inference path is fully feed-forward with optional mixed-precision and memory-efficient modes, making it practical to scale to long image sequences while keeping latency predictable. -
12
Stable Diffusion WebUI Docker
Easy Docker setup for Stable Diffusion with user-friendly UI
Stable Diffusion WebUI Docker is a Docker-based repository that simplifies running Stable Diffusion with rich user interfaces by packaging multiple popular web UIs into an easy-to-deploy containerized solution. It integrates leading community UIs like AUTOMATIC1111 and ComfyUI into a Docker Compose setup that can be started with a single command, abstracting away dependency installation and environment configuration. Users can choose which UI profile they want to run — for example, full... -
13
Claude Relay Service
Claude Code image, a one-stop open source transit service
...The project is designed to help users centralize subscriptions and API usage for services such as Claude, OpenAI, Gemini, and related tools. It acts as a middleware layer that forwards requests while managing authentication, routing, and cost-sharing scenarios. The system is particularly useful for teams or communities that want to pool access or simplify integration with different AI backends. Its architecture supports compatibility with native client tools so existing workflows can continue to function without major modification. ... -
14
Seamless Communication
Foundational Models for State-of-the-Art Speech and Text Translation
...The system architecture includes a real-time multimodal signal pipeline for audio, video, and sensor data, a dialog manager that can decide when to act (speak, gesture, point) or query, and a cross-modal reasoning layer that fuses perception with semantic context. The research prototype includes components for visual grounding (understanding when a user references something in view), gesture recognition and synthesis, and turn-taking mechanisms that mirror human conversational timing. Because latency and synchronization are critical, the codebase invests in asynchronous scheduling, overlap of perception and reasoning, and fast fallback responses. -
15
MiniMax-01
Large-language-model & vision-language-model based on Linear Attention
...It has 456 billion total parameters with 45.9 billion activated per token and is trained with advanced parallel strategies such as LASP+, varlen ring attention, and Expert Tensor Parallelism, enabling a training context of 1 million tokens and up to 4 million tokens at inference. MiniMax-VL-01 extends this core by adding a 303M-parameter Vision Transformer and a two-layer MLP projector in a ViT–MLP–LLM framework, allowing the model to process images at dynamic resolutions up to 2016×2016. -
16
Grok-1
Open-source, high-performance Mixture-of-Experts large language model
...The accompanying GitHub repository provides JAX example code for loading and running the model. Due to its substantial size, utilizing Grok-1 requires a machine with significant GPU memory. The repository's MoE layer implementation prioritizes correctness over efficiency, avoiding the need for custom kernels. This is a full repo snapshot ZIP file of the Grok-1 code. -
17
Qwen-VL
Chat & pretrained large vision language model
Qwen-VL is Alibaba Cloud’s vision-language large model family, designed to integrate visual and linguistic modalities. It accepts image inputs (with optional bounding boxes) and text, and produces text (and sometimes bounding boxes) as output. The model variants (VL-Plus, VL-Max, etc.) have been upgraded for better visual reasoning, text recognition from images, fine-grained understanding, and support for high image resolutions / extreme aspect ratios. Qwen-VL supports multilingual inputs... -
18
Qwen-Audio
Chat & pretrained large audio language model proposed by Alibaba Cloud
Qwen-Audio is a large audio-language model developed by Alibaba Cloud, built to accept various types of audio input (speech, natural sounds, music, singing) along with text input, and output text. There is also an instruction-tuned version called Qwen-Audio-Chat which supports conversational interaction (multi-round), audio + text input, creative tasks and reasoning over audio. It uses multi-task training over many different audio tasks (30+), and achieves strong multi-benchmarks performance... -
19
DeepSeek LLM
DeepSeek LLM: Let there be answers
...According to the evaluation files, DeepSeek LLM 67B Chat achieves strong performance on math benchmarks under both chain-of-thought (CoT) and tool-assisted reasoning modes. The model is trained from scratch, reportedly on a vast multilingual + code + reasoning dataset, and competes with other open or open-weight models. The architecture mirrors established decoder-only transformer families: pre-norm structure, rotational embeddings (RoPE), grouped query attention (GQA), and mixing in languages and tasks. ... -
20
ConvNeXt V2
Code release for ConvNeXt V2 model
...The V2 version introduces a fully convolutional masked autoencoder (FCMAE) framework where parts of the image are masked and the network reconstructs the missing content, marrying convolutional inductive bias with powerful pretraining. A key innovation is a new Global Response Normalization (GRN) layer added to the ConvNeXt backbone, which enhances feature competition across channels. The result is a convnet that competes strongly with transformer architectures on recognition benchmarks while being efficient and hardware-friendly. The repository provides official PyTorch implementations for multiple model sizes (Atto, Femto, Pico, up through Huge), conversion from JAX weights, code for pretraining/fine-tuning, and pretrained checkpoints. ... -
21
LaMDA-pytorch
Open-source pre-training implementation of Google's LaMDA in PyTorch
Open-source pre-training implementation of Google's LaMDA research paper in PyTorch. The totally not sentient AI. This repository will cover the 2B parameter implementation of the pre-training architecture as that is likely what most can afford to train. You can review Google's latest blog post from 2022 which details LaMDA here. You can also view their previous blog post from 2021 on the model. -
22
Hunyuan-A13B-Instruct
Efficient 13B MoE language model with long context and reasoning modes
...It supports up to 256K context tokens, advanced reasoning (CoT) abilities, and agent-based workflows with tool parsing. The model offers both fast and slow thinking modes, letting users trade off speed for deeper reasoning. It excels in mathematics, science, coding, and multi-turn conversation tasks, rivaling or outperforming larger models in several areas. Deployment is supported via TensorRT-LLM, vLLM, and SGLang, with Docker images and integration guides provided. Open-source under a custom license, it's ideal for researchers and developers seeking scalable, high-context AI capabilities with optimized inference. -
23
Gemma 4
Google’s flagship dense multimodal model for coding and reasoning
...The model contains approximately 30.7B parameters and supports text and image inputs with text generation output, while also processing video as image-frame sequences. Built as the most capable model in the Gemma 4 family, it combines strong reasoning performance with a large 256K-token context window and configurable thinking modes. Gemma 4 31B supports native function calling, structured outputs, and more than 140 languages, making it suitable for enterprise assistants, coding agents, document analysis, and multilingual applications. Google positions it as a frontier-level model that can run on consumer GPUs and workstations while achieving leading results across reasoning, mathematics, coding, and multimodal benchmarks. -
24
DeepSeek-V4-Pro
Flagship MoE model for advanced reasoning, coding, and agents
...DeepSeek-V4-Pro is positioned as the high-end variant of the V4 family, outperforming most open-source models in areas such as agentic coding, STEM reasoning, and world knowledge, and approaching the performance of leading closed-source systems. It also supports advanced reasoning modes and tool-based workflows, enabling autonomous task execution. -
25
DeepSeek-V4-Flash
Efficient MoE model for million-token reasoning and coding
...It is trained on more than 32T tokens and refined through a post-training pipeline that includes supervised fine-tuning, reinforcement learning, domain-specific expert cultivation, and on-policy distillation. DeepSeek-V4-Flash supports non-think, think, and think-max reasoning modes, allowing users to balance speed and depth. It is smaller than DeepSeek-V4-Pro but can approach Pro-level reasoning.