Trending repositories for topic fine-tuning
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
OneTrainer is a one-stop solution for all your stable diffusion training needs.
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.
Kiln AI: the easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
Low-code framework for building custom LLMs, neural networks, and other AI models
A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
Run serverless GPU workloads with fast cold starts on bare-metal servers, anywhere in the world
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Kiln AI: the easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.
A fine-tuned model from Qwen2.5-1.5B-Instruct, capable of handling sensitive topics. / 从 Qwen2.5-1.5B-Instruct 微调，主要擅长处理色情话题
Create synthetic datasets for training and testing Language Learning Models (LLMs) in a Question-Answering (QA) context.
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
📚 Text Classification with LoRA (Low-Rank Adaptation) of Language Models - Efficiently fine-tune large language models for text classification tasks using the Stanford Sentiment Treebank (SST-2) data...
Explore a comprehensive collection of resources, tutorials, papers, tools, and best practices for fine-tuning Large Language Models (LLMs). Perfect for ML practitioners and researchers!
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
Scalable data pre processing and curation toolkit for LLMs
OneTrainer is a one-stop solution for all your stable diffusion training needs.
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Run serverless GPU workloads with fast cold starts on bare-metal servers, anywhere in the world
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning
This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models f...
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models f...
Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
Kiln AI: the easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.
OneTrainer is a one-stop solution for all your stable diffusion training needs.
A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
Run serverless GPU workloads with fast cold starts on bare-metal servers, anywhere in the world
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models f...
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Kiln AI: the easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.
A fine-tuned model from Qwen2.5-1.5B-Instruct, capable of handling sensitive topics. / 从 Qwen2.5-1.5B-Instruct 微调，主要擅长处理色情话题
Create synthetic datasets for training and testing Language Learning Models (LLMs) in a Question-Answering (QA) context.
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
🚀LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training
📚 Text Classification with LoRA (Low-Rank Adaptation) of Language Models - Efficiently fine-tune large language models for text classification tasks using the Stanford Sentiment Treebank (SST-2) data...
A python implementation of “Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Multi-Channel Conformer” [TASLP 2024]
A fine-tuned model from Qwen2-1.5B-Instruct, capable of handling sensitive topics like violence, explicit content. / 从 Qwen2-1.5B-Instruct 微调，能处理各类敏感话题
The code repository for the CURLoRA research paper. Stable LLM continual fine-tuning and catastrophic forgetting mitigation.
Explore a comprehensive collection of resources, tutorials, papers, tools, and best practices for fine-tuning Large Language Models (LLMs). Perfect for ML practitioners and researchers!
Run serverless GPU workloads with fast cold starts on bare-metal servers, anywhere in the world
A complete guide to start and improve your LLM skills in 2024 with little background in the field and stay up-to-date with the latest news and state-of-the-art techniques!
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
A C++ implementation of Open Interpreter, based on llama.cpp. / Open Interpreter 的 C++ 实现，基于 llama.cpp
A C++ implementation of Open Interpreter, based on llama.cpp. / Open Interpreter 的 C++ 实现，基于 llama.cpp
🚀LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
Open source data anonymization and synthetic data orchestration for developers. Create high fidelity synthetic data and sync it across your environments.
Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.
This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models f...
Run serverless GPU workloads with fast cold starts on bare-metal servers, anywhere in the world
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
A C++ implementation of Open Interpreter, based on llama.cpp. / Open Interpreter 的 C++ 实现，基于 llama.cpp
OneTrainer is a one-stop solution for all your stable diffusion training needs.
Browser automation system that uses AI-driven planning to navigate web pages and perform goals.
dstack is a lightweight, open-source alternative to Kubernetes & Slurm, simplifying AI container orchestration with multi-cloud & on-prem support. It natively supports NVIDIA, AMD, & TPU.
🚀LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models f...
Kiln AI: the easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.
A fine-tuned model from Qwen2.5-1.5B-Instruct, capable of handling sensitive topics. / 从 Qwen2.5-1.5B-Instruct 微调，主要擅长处理色情话题
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
A survey on harmful fine-tuning attack for large language model
Explore a comprehensive collection of resources, tutorials, papers, tools, and best practices for fine-tuning Large Language Models (LLMs). Perfect for ML practitioners and researchers!
Create synthetic datasets for training and testing Language Learning Models (LLMs) in a Question-Answering (QA) context.
Run serverless GPU workloads with fast cold starts on bare-metal servers, anywhere in the world
This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
A fine-tuned model from Qwen2-1.5B-Instruct, capable of handling sensitive topics like violence, explicit content. / 从 Qwen2-1.5B-Instruct 微调，能处理各类敏感话题
Use Large Language Models like OpenAI's GPT-3.5 for data annotation and model enhancement. This framework combines human expertise with LLMs, employs Iterative Active Learning for continuous improveme...
Browser automation system that uses AI-driven planning to navigate web pages and perform goals.
Scalable data pre processing and curation toolkit for LLMs
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
A JAX research toolkit for building, editing, and visualizing neural networks.
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
Browser automation system that uses AI-driven planning to navigate web pages and perform goals.
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
A library for easily merging multiple LLM experts, and efficiently train the merged LLM.
This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models f...
Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon
A fine-tuned model from Qwen2-1.5B-Instruct, capable of handling sensitive topics like violence, explicit content. / 从 Qwen2-1.5B-Instruct 微调，能处理各类敏感话题
A survey on harmful fine-tuning attack for large language model
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
Open source data anonymization and synthetic data orchestration for developers. Create high fidelity synthetic data and sync it across your environments.
Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.
🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦�...
A general fine-tuning kit geared toward diffusion models.
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
A JAX research toolkit for building, editing, and visualizing neural networks.
Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
OneTrainer is a one-stop solution for all your stable diffusion training needs.
Using Low-rank adaptation to quickly fine-tune diffusion models.
Low-code framework for building custom LLMs, neural networks, and other AI models
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
The official implementation of Self-Play Preference Optimization (SPPO)
A library for easily merging multiple LLM experts, and efficiently train the merged LLM.
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
Explore a comprehensive collection of resources, tutorials, papers, tools, and best practices for fine-tuning Large Language Models (LLMs). Perfect for ML practitioners and researchers!
Embedding Studio is a framework which allows you transform your Vector Database into a feature-rich Search Engine.
[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
Scalable data pre processing and curation toolkit for LLMs
Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon
A general fine-tuning kit geared toward diffusion models.
The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"
Open source data anonymization and synthetic data orchestration for developers. Create high fidelity synthetic data and sync it across your environments.
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
🚀LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training