Brief Details: A fine-tuned LoRA model built on FLUX.1-dev, specialized in generating highly detailed realistic images with 64 network dimensions and 32 alpha settings.
Brief Details: Florence-2-base PromptGen v2.0 is a lightweight image captioning model with 271M params, offering efficient VRAM usage and multiple caption generation modes for diverse applications.
Brief-details: Zero-shot image classification model combining LLM and CLIP capabilities. Achieves 16.5% boost in retrieval tasks. Built on EVA02 architecture.
BRIEF DETAILS: Ovis1.6-Gemma2-9B: A 10.2B parameter multimodal LLM combining SigLIP-400M vision encoder with Gemma2-9B, leading OpenCompass benchmark for models under 30B parameters.
Brief Details: A specialized LoRA model trained on FLUX.1-dev for generating detailed clothing images, featuring Florence-2-large captioning and optimized for fashion photography.
Brief Details: Apple's AIMv2-huge vision model with 681M parameters, achieving 87.5% ImageNet accuracy. Excellent for image feature extraction and classification tasks.
Brief-details: A Walking Dead-themed LoRA model for SDXL, optimized for generating apocalyptic and zombie-related imagery with specialized training on Walking Dead characters and scenes
BRIEF-DETAILS: A specialized LoRA model for FLUX.1 that generates 2.5D cartoon-style images with 64 network dimensions, trained on 15 images over 15 epochs.
Brief Details: A powerful vision-language model that extends CLIP capabilities using LLMs, featuring 579M parameters and state-of-the-art cross-modal performance.
Brief-details: A 12.2B parameter Mistral-based merged model optimized for creative writing and worldbuilding, combining multiple specialized models for enhanced narrative capabilities.
BRIEF DETAILS: Advanced Whisper variant optimized for verbatim transcription with precise word-level timestamps and filler detection, implemented in faster-whisper framework.
Brief-details: WhisperNER v1 - Joint speech recognition & named entity recognition model with 1.54B params. Trained on NuNER dataset for English ASR and open-type NER.
Brief Details: OLMo-2-1124-7B is a 7.3B parameter open language model with strong performance across tasks, featuring 4T training tokens and 32 attention layers, built by Allen AI.
Brief Details: TinyClick - A compact 271M param GUI automation agent built on Florence-2-base. Enables precise UI element clicking based on natural language commands.
BRIEF DETAILS: Tulu 3 8B is an open-source instruction-following LLM built on Llama 3.1, optimized for diverse tasks including MATH and GSM8K, with strong performance in reasoning and safety.
Brief Details: BERT-based keyword extraction model achieving 87.17% F1 score. Fine-tuned on English text with strong precision (85.65%) and recall (88.74%).
Brief Details: 3B parameter medical-focused Llama model fine-tuned on chat_doctor dataset, optimized for medical consultations and instruction-following tasks.
Brief-details: Text-to-image LoRA model trained on FLUX.1-dev base model, specialized in generating high-quality portraits of 'imtiyaz' with various styles and settings.
Brief-details: A 70B parameter LLM fine-tuned for human-preferred summarization across 7 domains, showing superior performance in faithfulness (94.2%) and conciseness (90.9%)
Brief-details: Bilingual Arabic-English sentence transformer model with 135M parameters, optimized for semantic textual similarity and embedding generation at 768 dimensions.
Brief-details: A massive 1.7T parameter LLaMA-based instruction-tuned model designed for high-performance language tasks. Notable for its enormous size and BF16 tensor format.
