Lam-2 is the second-generation small language model (SLM) developed based on the custom architecture Aricate V4. It performs excellently in question and answer tasks and has outstanding language coherence and creativity. Compared with the previous generation products, Lam-2 has significantly improved in grammatical correctness and text generation quality.

Natural Language ProcessingSafetensorsFrench

A medical reasoning-specific model fine-tuned based on the Gemma-3 1B model, supporting medical Q&A with step-by-step reasoning

Natural Language ProcessingTransformersEnglish

A specialized license plate detection model fine-tuned from Gemma 3 4B, demonstrating visual-language models can achieve localization without object detection pre-training

MultimodalTransformers

This is the result of task arithmetic fusion between Darkest-muse-v1 and gemma-2-9b-it-abliterated-LoRA-untied models using the mergekit tool

Natural Language ProcessingTransformers

A text-to-image diffusion model based on LoRA technology, capable of generating portraits with Ariana Grande's signature style.

Computer VisionDiffusers

LoRA model trained on AI-Toolkit (Flux.1 Dev Edition), specializing in high-precision character feature reproduction

Computer VisionDiffusers

A BitsAndBytes NF4 quantized version based on Aria-sequential_mlp, suitable for image-to-text tasks with approximately 15.5 GB VRAM requirement.

MultimodalTransformers

FP8 dynamically quantized model based on Aria-sequential_mlp, suitable for image-text-to-text tasks, requiring approximately 30GB VRAM.

MultimodalTransformers

This model is a pre-trained model based on the Transformers architecture, and its specific purpose and functionality require further information to confirm.

Natural Language ProcessingTransformers

An object detection model based on the YOLO11x architecture, specifically designed to recognize digits (0-10) and basic arithmetic operators (addition, subtraction, multiplication, division, etc.) in images.

This is an arithmetic reasoning model fine-tuned based on Meta's Llama 2 7B model, specifically optimized for the GSM8K mathematical problem dataset, and performs excellently in mathematical reasoning tasks.

Natural Language ProcessingTransformersEnglish

Llama3-ChatQA-1.5 is a dialogue Q&A and retrieval augmented generation model developed based on the Llama-3 base model, which performs excellently in dialogue QA and RAG tasks. This model adopts an improved training method and incorporates more dialogue Q&A data, enhancing the ability of table and arithmetic calculations.

Natural Language ProcessingTransformersEnglish

A 7B-parameter language model merged from Mistral 7B v0.1, combining multiple fine-tuned models via task arithmetic, supporting 32K context length, balancing creativity and reasoning

Natural Language ProcessingTransformers

Astrea-RP-v1-3B is a 3B-parameter large language model that integrates multiple models through task arithmetic, focusing on text generation tasks.

Natural Language ProcessingGgufEnglish

A font recognition model fine-tuned on ResNet-18, achieving 78.1% accuracy on the test set

Computer VisionTransformers

Arithmo2-Mistral-7B is a mathematical reasoning model fine-tuned based on Mistral-7B. It has significantly improved compared to the previous generation on the GSM8K and MATH benchmarks, and can perform mathematical reasoning and write Python programs to solve problems.

Natural Language ProcessingTransformersEnglish

ARIA 70B V2 is a large-scale language model based on the Llama 2 architecture, supporting French and English, with a focus on text generation tasks.

Natural Language ProcessingGgufMultiple Languages

This is a voice conversion model based on RVC (Retrieval-Based Voice Conversion) technology, capable of transforming input audio into Ariana Grande-style speech.

Audio ProcessingTransformers

This is a model based on sentence-transformers that maps sentences and paragraphs into a 64-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

Natural Language ProcessingPytorch

This is a model based on sentence-transformers that maps sentences and paragraphs into a 64-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

Natural Language ProcessingPytorch