Search Results for "tuning"
Sort By:
Showing 109 open source projects for "tuning"
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.
-
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
1
Gemma in PyTorch
The official PyTorch implementation of Google's Gemma models
gemma_pytorch provides the official PyTorch reference for running and fine-tuning Google’s Gemma family of open models. It includes model definitions, configuration files, and loading utilities for multiple parameter scales, enabling quick evaluation and downstream adaptation. The repository demonstrates text generation pipelines, tokenizer setup, quantization paths, and adapters for low-rank or parameter-efficient fine-tuning. -
2
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training
MedicalGPT training medical GPT model with ChatGPT training pipeline, implementation of Pretraining, Supervised Finetuning, Reward Modeling and Reinforcement Learning. MedicalGPT trains large medical models, including secondary pre-training, supervised fine-tuning, reward modeling, and reinforcement learning training. -
3
InstantCharacter
Personalize Any Characters with a Scalable Diffusion Transformer
InstantCharacter is a tuning-free diffusion transformer framework created by Tencent Hunyuan / InstantX team, which enables generating images of a specific character (subject) from a single reference image, preserving identity and character features. Uses adapters, so full fine-tuning of the base model is not required. Demo scripts and pipeline API (via infer_demo.py, pipeline.py) included. -
4
MiniCPM5-2B
SOTA on-device LLMs, small yet powerful
...The repository includes base, supervised fine-tuned, and deployment-ready model variants. Quantized releases are available in formats such as GGUF, MLX, GPTQ, and DSpark. It also provides fine-tuning, quantization, deployment, and agent-skill resources for adapting models to different environments. Earlier MiniCPM releases explore sparse attention, mixture-of-experts designs, long-context modeling, and efficient edge inference. -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
CogView4
CogView4, CogView3-Plus and CogView3(ECCV 2024)
...Compared to previous CogView versions, CogView4 introduces architectural upgrades, improved training pipelines, and larger-scale datasets, enabling stronger alignment between textual prompts and generated visual content. It emphasizes bilingual usability, making it well-suited for cross-lingual multimodal applications. The model also supports fine-tuning and downstream customization, extending its applicability to creative content generation, human–computer interaction, and research on vision-language alignment. -
6
DeepSeek-V3
Powerful AI language model (MoE) optimized for efficiency/performance
...The model introduces an auxiliary-loss-free load balancing strategy and a multi-token prediction training objective to boost performance. Trained on 14.8 trillion diverse, high-quality tokens, DeepSeek-V3 underwent supervised fine-tuning and reinforcement learning to fully realize its capabilities. Evaluations indicate that it outperforms other open-source models and rivals leading closed-source models, achieving this with a training duration of 55 days on 2,048 Nvidia H800 GPUs, costing approximately $5.58 million. -
7
DeepSeek R1
Open-source, high-performance AI model with advanced reasoning
...The model employs a Mixture of Experts (MoE) architecture, comprising 671 billion total parameters with 37 billion active parameters per token, and supports a context length of up to 128,000 tokens. DeepSeek-R1's training regimen uniquely integrates large-scale reinforcement learning (RL) without relying on supervised fine-tuning, enabling the model to develop advanced reasoning capabilities. This approach has resulted in performance comparable to leading models like OpenAI's o1, while maintaining cost-efficiency. To further support the research community, DeepSeek has released distilled versions of the model based on architectures such as LLaMA and Qwen. -
8
MetaCLIP
ICLR2024 Spotlight: curation/training code, metadata, distribution
...The goal is to preserve CLIP’s strong zero-shot transfer capability while enabling fast adaptation to domain shifts or novel class sets with minimal data and without catastrophic forgetting. The repository provides training logic, adaptation strategies (e.g. prompt tuning, adapter modules), and evaluation across base and target domains to measure how well the model retains its general knowledge while specializing as needed. It includes utilities to fine-tune vision-language embeddings, compute prompt or adapter updates, and benchmark across transfer and retention metrics. MetaCLIP is especially suited for real-world settings where a model must continuously incorporate new visual categories or domains over time. -
9
CogVideo
Text and image to video generation: CogVideoX and CogVideo
...The latest CogVideoX models offer higher resolution outputs, longer video durations, and improved controllability through prompt engineering. The project includes tools for inference, fine-tuning, and optimization, making it suitable for both research and production use. It supports efficient deployment on a range of GPUs, including consumer hardware with quantization techniques. Overall, CogVideo provides a powerful framework for generating high-quality AI videos and experimenting with cutting-edge multimodal AI systems. -
$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.
-
10
HY-Motion 1.0
HY-Motion model for 3D character animation generation
...Built on advanced deep learning architectures that combine Diffusion Transformer (DiT) and flow matching techniques, HY-Motion scales these approaches to the billion-parameter level, resulting in strong instruction-following capabilities and richer motion outputs compared to existing open-source models. The training strategy for the HY-Motion series includes extensive pre-training on thousands of hours of varied motion data, fine-tuning on curated high-quality datasets, and reinforcement learning with human feedback, which improves both the plausibility and adaptability of generated motion sequences. -
11
FinGPT
Open-Source Financial Large Language Models
...It extends traditional GPT-style models by connecting them to live or historical financial datasets, news APIs, and economic indicators so that outputs are grounded in relevant and recent market conditions rather than generic knowledge alone. The platform typically includes tools for fine-tuning, context engineering, and prompt templating, enabling users to build specialized assistants for tasks like sentiment analysis, earnings summary generation, risk profiling, trading signal interpretation, and document extraction from financial reports. -
12
fast-stable-diffusion
Fast-stable-diffusion + DreamBooth
...Rather than being a standalone packaged application, this project offers ready-to-use interactive notebooks that install and launch full-feature Stable Diffusion web UIs inside Colab without requiring complex local setups or GPU installations. Users can run both AUTOMATIC1111’s interface and ComfyUI workflows with minimal configuration, experiment with DreamBooth fine-tuning, and explore features like text-to-image generation, inpainting, and image-to-image transformations all within a browser session. Because it is configured for Colab, the project leverages Colab’s hosted GPUs, making it possible to use Stable Diffusion even without a powerful local GPU. -
13
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
GLM-4.5 is a cutting-edge open-source large language model designed by Z.ai for intelligent agent applications. 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... -
14
HunyuanVideo-I2V
A Customizable Image-to-Video Model based on HunyuanVideo
...The repository includes pretrained weights, inference and sampling scripts, training code for LoRA effects, and support for parallel inference via xDiT. Resolution, video length, stability mode, flow shift, seed, CPU offload etc. Parallel inference support using xDiT for multi-GPU speedups. LoRA training / fine-tuning support to add special effects or customize generation. -
15
Kev
Jev-like family of decision models built on top of Qwen3.5/3.8
Kev is a family of open decision models inspired by Jev and built on Qwen3.5 and Qwen3.8 foundations. It processes a document together with multiple typed questions and returns probabilities instead of generated prose. Supported question formats include yes-or-no, multiple choice, and ordered scoring. Checkpoints range from a compact 0.8B model for smaller hardware to a 27B version for high-end systems. The models include probability calibration and can run through CUDA, ROCm, or MLX... -
16
LTX-2.3
Official Python inference and LoRA trainer package
LTX-2.3 is an open-source multimodal artificial intelligence foundation model developed by Lightricks for generating synchronized video and audio from prompts or other inputs. Unlike most earlier video generation systems that only produced silent clips, LTX-2 combines video and audio generation in a unified architecture capable of producing coherent audiovisual scenes. The model uses a diffusion-transformer-based architecture designed to generate high-fidelity visual frames while... -
17
fairseq2
FAIR Sequence Modeling Toolkit 2
...Built from the ground up for scalability, composability, and research flexibility, fairseq2 supports a broad range of language, speech, and multimodal content generation tasks, including instruction fine-tuning, reinforcement learning from human feedback (RLHF), and large-scale multilingual modeling. Unlike the original fairseq—which evolved into a large, monolithic codebase—fairseq2 introduces a clean, plugin-oriented architecture designed for long-term maintainability and rapid experimentation. It supports multi-GPU and multi-node distributed training using DDP, FSDP, and tensor parallelism, capable of scaling up to 70B+ parameter models. ... -
18
CogVLM2
GPT4V-level open-source multi-modal model based on Llama3-8B
...It supports bilingual interaction (Chinese and English) and has open-source versions optimized for dialogue and video comprehension. Notably, the Int4 quantized version allows efficient inference on GPUs with only 16GB of memory. The repository offers demos, API servers, fine-tuning examples, and integration with OpenAI API-compatible endpoints, making it accessible for both researchers and developers. -
19
Hunyuan3D-2.1
From Images to High-Fidelity 3D Assets
...It improves on prior versions by using a PBR texture pipeline (enabling realistic material effects like reflections and subsurface scattering) and allowing community fine-tuning and extension. It supports both shape generation (mesh geometry) and texture generation modules. Physically Based Rendering texture synthesis to model realistic material effects, including reflections, subsurface scattering, etc. Cross-platform support (MacOS, Windows, Linux) via Python / PyTorch, including diffusers-style APIs. -
20
DINOv3
Reference PyTorch implementation and models for DINOv3
...The model supports multiple backbone architectures, including Vision Transformers (ViT), and can handle larger image resolutions with improved stability during training. The learned embeddings generalize robustly across tasks like classification, retrieval, and segmentation without fine-tuning, showing state-of-the-art transfer performance among self-supervised models. -
21
Tongyi DeepResearch
Tongyi Deep Research, the Leading Open-source Deep Research Agent
...It’s built to act like a research agent: synthesizing, reasoning, retrieving information via the web and documents, and backing its outputs with evidence. The model is about 30.5 billion parameters in size, though at any given token only ~3.3B parameters are active. It uses a mix of synthetic data generation, fine-tuning and reinforcement learning; supports benchmarks like web search, document understanding, question answering, “agentic” tasks; provides inference tools, evaluation scripts, and “web agent” style interfaces. The aim is to enable more autonomous, agentic models that can perform sustained knowledge gathering, reasoning, and synthesis across multiple modalities (web, files, etc.). -
22
DramaBox
super expressive prompting model based on ltx2.3
DramaBox is an expressive text-to-speech and voice cloning project from Resemble AI built on top of the LTX-2.3 audio branch. It generates speech from prompts that control not only the spoken text, but also speaker identity, emotion, delivery style, laughs, sighs, pauses, and transitions. Users can optionally provide a voice reference of around 10 seconds or more to clone the target timbre while still guiding performance through scene-style prompting. The project includes a warm inference... -
23
DeepSeek-V3.2-Exp
An experimental version of DeepSeek model
DeepSeek-V3.2-Exp is an experimental release of the DeepSeek model family, intended as a stepping stone toward the next generation architecture. The key innovation in this version is DeepSeek Sparse Attention (DSA), a sparse attention mechanism that aims to optimize training and inference efficiency in long-context settings without degrading output quality. According to the authors, they aligned the training setup of V3.2-Exp with V3.1-Terminus so that benchmark results remain largely... -
24
Hy-MT2 is a family of fast-thinking multilingual translation models built for complex real-world translation scenarios. It includes 1.8B, 7B, and 30B-A3B model sizes, giving users options for lightweight deployment, stronger general performance, or MoE-based capacity. The models support translation across 33 languages and are designed to follow detailed translation instructions in multiple languages. They can handle tasks involving terminology, style, personalization, delimiters, structured...
-
25
Cactus Needle
26m function call model that runs on incredibly small devices
Needle is an experimental 26-million-parameter function-calling model designed to run on extremely small devices such as phones, watches, glasses, and low-power personal AI hardware. It is based on a Simple Attention Network architecture and was distilled from a much larger model to focus on fast, compact tool-use behavior. The project provides open weights, training details, dataset generation resources, and a playground for testing the model with custom tools. Needle is optimized for...
