Fine-tuning 25

A powerful, open-source LLM with various fine-tuned models for specific applications. Mistral 7B is a large language model (LLM) created by Mistral AI, designed to be powerful and adaptable for various use-cases. It outperforms Llama 2 13B on benchmarks and features natural coding abilities and an 8k sequence length. Numerous fine-tuned models based on Mistral 7B are available, each tailored for specific applications like occult knowledge, scientific reasoning, or role-playing.

Tailor-made AI image generation platform with fine-tuning and generative filters. Astria is a platform that offers tailor-made AI image generation through its Dreambooth API. It allows users to create custom images using AI, fine-tuning models like Flux, Stable Diffusion 1.5 (SD1.5), and Stable Diffusion XL (SDXL) to generate personalized results for specific subjects or styles. Astria provides various fine-tuning options, including Checkpoint and LoRAs, and offers a FaceID-like alternative for lower fidelity results with less processing time. The platform also features generative filters for artistic effects and supports use cases like AI photoshoots, virtual try-ons, mobile apps, product shots, and interior design.

Terracotta simplifies LLM experimentation with a unified platform for training and evaluation. Terracotta is a platform designed to simplify and accelerate the process of experimenting with Large Language Models (LLMs). It streamlines the training and evaluation of LLMs by providing a unified interface for managing models, data, and evaluations. Terracotta aims to supercharge the LLM iteration process, making it more intuitive and efficient.

Open-source platform for tracing and evaluating AI applications. Laminar is an open-source platform designed for tracing and evaluating AI applications. It allows developers to build, deploy, and monitor next-generation AI apps with features like complex async pipelines, a fast Rust backend, version control for production releases, and zero-latency-overhead logs for monitoring each pipeline node. Laminar provides observability, evals, and browser agent capabilities to help developers build reliable AI products.

A platform for fast inference of generative AI models, including fine-tuning and deployment. Fireworks AI is a platform designed to provide the fastest inference for generative AI models. It allows users to utilize state-of-the-art, open-source LLMs and image models at high speeds. Users can fine-tune and deploy their own models at no additional cost. The platform offers a range of tools and infrastructure to build and deploy generative AI applications, including model APIs, customization options, and compound AI systems.

Cloud solutions for AI development, training, and inference with various AI accelerators. Cirrascale Cloud Services provides cloud-based solutions to accelerate AI development, training, and inference workloads. It offers a platform to test and deploy on various leading AI accelerators, including AMD Instinct, Cerebras, NVIDIA GPU, and Qualcomm Cloud AI. The company focuses on delivering high throughput, multi-tiered storage, professional and managed services, and high bandwidth, low-latency networking.

No-code platform to create, manage, and optimize custom AI models for businesses. Entry Point is a no-code platform that helps you create custom AI models for your business or projects. Manage training data, generate synthetic examples, estimate fine-tuning costs, and optimize models — all in one place! Train, manage, and evaluate custom large language models (LLMs) fast and efficiently on Entry Point AI with no code required.

AI coding assistant for enterprises with self-hosting and fine-tuning capabilities. CodeComplete is building an AI coding assistant for enterprise customers. It offers self-hosting to address security concerns, and is fine-tuned to the company's codebase and coding style to better integrate into developer workflow. It provides features like code generation, code chat, automated unit test generation, automated documentation, and refactoring & migrations. Customization is available with fine-tuning and retrieval augmented generation (RAG).

A directory for discovering AI infrastructure tools and services. Infrabase.ai is a directory for discovering AI infrastructure tools and services. It provides a resource focused on helping users find the components for their AI projects, whether they're seeking alternatives to existing solutions or exploring new AI infrastructure products. It aims to be the destination for understanding the AI infrastructure landscape.

Platform to fine-tune and monetize open-source AI models with one click. Bakery is the first platform built on Bagel architecture that lets developers fine-tune and monetize open-source AI models with one click. It allows users to transform any open-source model into their own monetizable API endpoint. It caters to AI startups, ML engineers, and researchers.

Collaborative tool for running large language models by distributing model parts. An open source tool for running large language models like BLOOM-176B collaboratively. Users load a small part of the model and team up with others serving the other parts to run inference or fine-tuning.

HyperLLM offers tools for training, tuning, and deploying efficient language models and retrieval-based AI applications. HyperHRT introduces a new generation of language model architecture developed at the Indian Institute of Technology, Patna that you can train & tune and integrate with a small-language model. HyperHRT works on real-time decentralised fine-tuning approach. HyperCrawl is a part of HyperLLM where they are dedicated to build the infrastructure for a world of future LLMs. Models that requires less computational resources & outperforms any models available. Exthalpy is serverless retrieval to power the future of AI. Build retrieval-first AI applications and models that are less dependent on computation-heavy training processes.

No-code platform for building OpenAI apps with fine-tuning and long-term memory. Trudo.ai is a no-code platform for building OpenAI apps. It allows users to fine-tune GPT3 models with a spreadsheet (multiple columns & JSON compatible). It also offers memory powered by embeddings & ChatGPT, enabling users to upload any file (cvs, txt & pdf) and extract it later. Trudo AI provides an intuitive UI for building complex AI applications on top of OpenAI, supporting integrations with Zapier, Make.com, and more.

Create AI art with fine-tuned models and custom training using Dreambooth. Create amazing AI art with multiple fine-tunes of different models. Train a custom model on top of fine-tunes using Dreambooth and put yourself into the world of AI.

Platform to fine-tune AI models and create custom AIs. FyneTuner AI is a platform that allows users to easily fine-tune AI models and create custom AIs with only a few inputs. It offers simple pricing to get users started, with an exclusive early bird offer.

BreveAI: LLMs integrated with real-world data, focusing on efficiency and open-source adoption. BreveAI offers a distinctive approach to large language models (LLMs) by integrating with real-world data and prioritizing task efficiency. It emphasizes open-source adoption with an easy API. BreveAI's pricing is transparent, claiming to be 30% lower than current LLMs with 40% higher accuracy. It provides models that simplify complex tasks like prompt engineering, evaluation, RAG, fine-tuning, and deployment, allowing users to maximize AI's benefits with minimal effort. BreveAI's models are specifically trained on business language to deliver unparalleled accuracy and efficiency.

Cols AI provides AI voice call solutions and a GenAI platform for data integration. Cols AI offers AI voice call solutions, including AI voice assistants with sub-1000ms latency for real-time handling of complex tasks and efficient customer problem-solving during calls. They provide AI calling software and voice agents. Cols AI also offers a data engine that powers foundation models and a GenAI platform that leverages data to unlock the value of AI through fine-tuning, RLHF, and integration of enterprise data sources. They support all foundation models.

No-code AI platform to build, experiment, and deploy AI applications easily. Riku.AI is a no-code AI platform that empowers users to build, experiment, test, and deploy AI applications without writing any code. It offers integrations, an API, and public share links to make AI accessible to everyone. Users can build chat, text, vision, and image apps through a simple-to-use interface. The platform provides access to 40+ world-class Large Language Models (LLMs) and allows users to connect siloed data sources securely. Riku.AI enables businesses to embed generative AI workflows, automate repetitive tasks, and rapidly test ideas.

A resource hub for prompt engineering tutorials, trends, and AI strategies. PromptEngineering.org, also known as The Prompt Engineering Institute, is a platform dedicated to providing the latest tutorials, resources, trends, products, and services related to prompt engineering. It offers insights into high-impact AI strategies with real-world applications, aiming to help users stay ahead of AI trends and maximize productivity without information overload. The site features lessons, a prompt library, and articles covering prompt engineering, large language models (LLMs), and AI agents.

Open-source fine-tuning & reinforcement learning for LLMs. 🦥 Unsloth makes it super easy for you to train text-to-speech (TTS), diffusion, multimodal/image and text models like Llama 3 100% locally or for free on platforms such as Google Colab and Kaggle. We streamline the entire training workflow, including model loading, quantizing, training, evaluating, running, saving, exporting, and integrations with inference engines like Ollama, llama.cpp, and vLLM.

A library for browsing and comparing Flux LoRA models to enhance Flux model generation. Flux-lora.com is a platform dedicated to cataloging and providing access to Flux LoRA models. It allows users to browse and compare the latest Flux LoRA models to enhance their Flux model generation experience. The site aims to help users find and utilize Flux LoRA models suitable for their specific projects.

Enterprise LLM platform for developing and controlling custom LLMs with high accuracy. Lamini is an enterprise LLM platform designed for software teams to develop and control their own LLMs. It offers built-in best practices for specializing LLMs on proprietary documents, improving performance, reducing hallucinations, offering citations, and ensuring safety. Lamini can be installed on-premise or on clouds securely and is the only platform for running LLMs on AMD GPUs and scaling to thousands with confidence.

Semiring simplifies building and deploying custom ML models with minimal data and expertise. Semiring is a platform that enables users to build and deploy custom ML models easily, even without prior ML expertise. It streamlines the process from crafting datasets with as few as 5 data samples to fine-tuning models and deploying them via a simple API.

A job search engine for Machine Learning and Data Science roles. This job search engine exclusively shows Machine Learning and Data Science jobs and is tailored to tag and process sector specific skills (fine-tuning, model optimization), frameworks (e.g. Pytorch, LlamaIndex) and acronyms. We update the live jobs listed from over 50,000 companies each hour. It contains a custom LLM/Retrieval Augmented Generation (RAG) model to query our full jobs database with natural language. Discover AI and Machine Learning jobs at Towards AI Jobs. Find a comprehensive list of job openings in the AI field and progress your career in artificial intelligence.