BRIEF-DETAILS: Specialized 4B parameter variant of Google's Gemma optimized for neutral information retrieval, featuring reduced moral bias and enhanced analytical capabilities
BRIEF-DETAILS: Multilingual ASR model supporting 40 Eastern languages and 22 Chinese dialects, with 140M parameters. Features voice detection, segmentation, and language ID capabilities.
Brief-details: NVIDIA's 12B parameter multimodal model that enriches text prompts based on video context, designed for commercial use with enhanced detail generation capabilities.
Brief-details: Uncensored version of Google's Gemma-3B-IT created through abliteration technique, designed to remove content refusals while maintaining core functionality
Brief-details: A 70B parameter LLM fine-tuned from Llama-3.3, focused on crypto-positive and freedom-aligned responses. Known for unfiltered, personality-driven interactions.
Brief Details: Japanese language model based on DeepSeek-R1-Distill-Qwen-32B, converted to GGUF format for efficient local deployment using llama.cpp
BRIEF-DETAILS: Quantized versions of teapotllm offering various compression levels (Q2-Q8) in GGUF format, optimized for efficient deployment with sizes ranging from 0.2-0.6GB
Brief Details: Fast, static embedding model distilled from bge-base-en-v1.5, optimized for real-time performance with 32M vocabulary size. Achieves 51.66% average on MTEB benchmarks.
Brief Details: Ruri-base is a Japanese text embedding model with 111M parameters, achieving 71.91% avg. performance on JMTEB benchmarks. Optimized for semantic search and text similarity.
BRIEF DETAILS: A Long-T5 model fine-tuned for scientific text simplification, specializing in converting complex research papers into lay-friendly summaries. ROUGE-1: 49.15
Brief-details: MS Paint-style image generation model that intentionally creates "bad" artwork, perfect for meme-like and nostalgic digital art aesthetics
BRIEF DETAILS: NVIDIA's quantized 8B parameter LLaMA model optimized for FP8 precision, offering 1.3x speedup on H100 GPUs while maintaining strong performance across benchmarks.
Brief Details: SDXL LoRA model that applies Studio Ghibli-style artistic effects with adjustable strength (-3 to +3), optimized for SDXL pipeline integration.
Brief-details: Cross-encoder reranking model based on ELECTRA, optimized for text ranking tasks. Specializes in reordering passages for retrieve-rerank pipelines.
Brief Details: Japanese-optimized AI VTuber assistant based on Gemma-3B-4B, specialized in multi-turn conversations with personality traits and image understanding capabilities.
BRIEF-DETAILS: BERT-based NER model specialized for trip planning, extracting origin, destination & transport mode from natural language queries. Ideal for travel apps.
Brief-details: BlackSheep-24B is a 24B parameter LLM known for high willingness scores (9.5/10) and specialized layers 6-20, designed for controlled hallucinations and alignment research.
Brief-details: Spanish clinical language model built on RigoBERTa 2, trained on ClinText-SP corpus (26M tokens). Optimized for medical NLP tasks with state-of-the-art performance.
Brief Details: Gemma 3 1B quantized model optimized for inference, featuring 4-bit precision, multimodal capabilities, and 32K context window.
Brief-details: An AI model hosted by omar07ibrahim on Hugging Face, with limited public information available. Purpose and capabilities require further documentation.
Brief-details: A fine-tuned variant of TinyLlama optimized for 2x faster performance using Unsloth and TRL library, developed by omar07ibrahim under Apache-2.0 license.