Pola Photo (Flux Dev) is an image generation model based on Flux.1-dev, specifically designed to generate realistic images with the style of Polaroid instant photos. This model is trained on the Replicate platform using open-source materials and follows the CC non-commercial attribution license agreement.

Computer VisionDiffusers

A LoRA model specifically trained to replicate the classic rubber hose animation style of the 1920-1930s

Computer VisionDiffusers

A dialogue model fine-tuned based on Gemma 27b, aiming to replicate the text quality of Claude 3, supporting ChatML format for conversational interactions.

Natural Language ProcessingGgufEnglish

A large language model fine-tuned based on Mistral-Nemo-Instruct, designed to replicate the exquisite prose quality of Claude 3 models

Natural Language ProcessingTransformersEnglish

Magnum V4 72B is a member of the model series built on Qwen, aiming to replicate the prose quality of the Claude 3 series models and suitable for local AI chat applications.

Natural Language ProcessingTransformersEnglish

CursorCore is a series of open-source models designed specifically for AI-assisted programming, aiming to support functions such as automatic editing and inline chat, and replicate the core capabilities of closed-source AI-assisted programming tools like Cursor. This model is fine-tuned based on Qwen2.5-Coder-1.5B, and achieves programming assistance functions by aligning programming instruction generation data.

Natural Language ProcessingTransformersOther

This is a large language model designed to replicate the prose quality of the Claude 3 model (especially Sonnet and Opus). It is obtained through multiple KTO runs and one SFT run and supports the ChatML format.

Natural Language ProcessingTransformers

Magnum is a large language model fine-tuned based on Mistral-Large-Instruct-2407, aiming to replicate the prose quality of the Claude 3 model. This is the sixth version in this series of models, focusing on providing high-quality text generation capabilities and supporting multiple languages.

Natural Language ProcessingGgufMultiple Languages

This model is a large language model fine-tuned based on Qwen-2 72B Instruct, aiming to replicate the prose quality of the Claude 3 series of models and is the seventh version in the series of models.

Natural Language ProcessingSafetensorsMultiple Languages

This is a model fine-tuned based on Mistral-Large-Instruct-2407, aiming to replicate the prose quality of the Claude 3 series models (especially Sonnet and Opus).

Natural Language ProcessingTransformersMultiple Languages

The Kodak model perfectly replicates the nostalgic essence of early 1990s photography, evoking memories of disposable cameras and carefree travels.

Computer VisionDiffusers

v2.5 KTO is a model focused on text generation, aiming to replicate the prose quality of the Claude 3 series models (especially Sonnet and Opus). It supports multiple languages including Chinese, English, French, etc.

Natural Language ProcessingSafetensorsMultiple Languages

This project is an important achievement of the Anthracite Organization in the field of text generation, aiming to replicate the prose quality of the Claude 3 series models.

Natural Language ProcessingGgufMultiple Languages

magnum-v2-12b is the fourth model in the series, aiming to replicate the text quality of the Claude 3 series models (especially Sonnet and Opus). It is fine-tuned based on Mistral-Nemo-Base-2407 and has powerful text generation capabilities.

Natural Language ProcessingSafetensorsMultiple Languages

Mini Magnum is a streamlined version of magnum-72b-v1, aiming to replicate the text quality of the Claude 3 series (especially Sonnet and Opus). It is fine-tuned based on Mistral-Nemo-Base-2407, and a new general instruction dataset is added to improve coherence and alignment.

Natural Language ProcessingTransformersMultiple Languages

A model fine-tuned based on Qwen-2 72B Instruct, aiming to replicate the prose quality of Claude 3 models

Natural Language ProcessingTransformersMultiple Languages

Dolphin-2.2.1-mistral-7b is a powerful dialogue model based on the MistralAI architecture, with excellent dialogue and empathy capabilities. AshhLimaRP-Mistral-7B is a chat model specifically designed for long-format role-playing, aiming to replicate the forum-style role-playing experience. Both are based on the Mistral-7B architecture and use the Apache-2.0 license.

Natural Language ProcessingTransformers

This model is an attempt to replicate the Dragon model from 'AI Dungeon 2', trained on the text_adventures.txt dataset from the original 'AI Dungeon 2' GitHub version, aiming to restore the characteristics of the Dragon model built on GPT3 175B in 2020.

Natural Language ProcessingTransformers

This is a voice conversion model based on RVC (Retrieval-based Voice Conversion) technology, specifically trained for 1000 epochs to replicate Michael Jackson's voice.

Audio ProcessingTransformers

The Alpaca model replicated by the Tatsu team at Stanford University. This is a large language model that performs instruction fine-tuning based on LLaMA-7B. The model was trained on 4 A100 GPUs for 6 hours, with computing power donated by redmond.ai. It does not use LoRA technology and adopts the native fine-tuning method.

Natural Language ProcessingTransformers