Brief-details: A specialized model focused on identifying and handling PII (Personally Identifiable Information) and PHI (Protected Health Information) in text, developed by anhphamduy
Brief-details: OCR model by vikp for text recognition, specifically designed for the Surya project. Hosted on HuggingFace, focused on optical character recognition tasks.
Brief-details: SDXL 0.9 Refiner - Stability AI's advanced image refinement model for enhancing details and quality of Stable Diffusion XL outputs
BRIEF DETAILS: PISCO-solar is a 10.9B parameter context compression model optimized for RAG QA, featuring 16x compression and 5x faster inference with minimal accuracy loss.
Brief-details: GGUF-quantized version of hunyuan-video model for text-to-video generation, specialized in anime-style content creation with specific model requirements and workflows
BRIEF DETAILS: Game asset generation LoRA model specializing in 3D isometric objects, characters, and fantasy items with white backgrounds for game developers and artists.
BRIEF DETAILS: Fine-tuned FLAN-T5-Large model for extractive QA, trained on SQuAD2.0. Achieves 86.79% exact match accuracy. Requires <cls> token prefix.
Brief-details: MobileNetV2 variant trained on ImageNet-1k using RandAugment recipe. Efficient architecture with 3.5M params, optimized for mobile/edge deployment with strong accuracy-efficiency trade-off.
BRIEF DETAILS: A Q6_K GGUF quantized version of DeepSeek-R1-Distill-Qwen-32B-Uncensored, optimized for efficient deployment while maintaining performance.
Brief-details: A prompt expansion model by ghunkins, designed to enhance and elaborate input prompts for improved AI interactions, available on HuggingFace.
Brief Details: Llama-2-13b is Meta's advanced 13B parameter language model, part of the Llama 2 family, offering strong performance for various NLP tasks
BRIEF-DETAILS: WeShop UI 1.0.0 - An open-source local AI image generation solution built on Stable Diffusion WebUI, featuring SDXL support, batch processing, and multi-GPU capabilities.
Brief-details: Speech emotion recognition foundation model with ~300M parameters capable of analyzing 9 emotion categories from audio, trained on 42K+ hours of data
Brief-details: VRAM-40 is an AI model by unslothai focused on optimized VRAM usage, available on HuggingFace, designed for efficient memory management in AI applications
Brief-details: Llama-3.3-70B-Instruct-AWQ is a 4-bit quantized version of Meta's powerful 70B parameter LLM, optimized for efficient deployment while maintaining performance.
Brief-details: An AI model for detecting acne severity across 6 levels (clear to very severe), offering automated skin condition assessment with clinical precision.
BRIEF-DETAILS: Multilingual embedding model optimized for text representation across languages, available in various GGUF quantizations (q4-f16), recommended for q6_k/q8_0 usage
Brief-details: VRAM-80 is a model by unslothai focused on optimizing VRAM usage and efficiency, available on HuggingFace platform
Brief-details: A compact CLIP text encoder model developed by peft-internal-testing, designed for efficient text embedding and multimodal applications.
Brief-details: 8B parameter Llama 3.1 model optimized with FP8 quantization, achieving 99.52% accuracy recovery while reducing memory footprint by 50%
Brief Details: Cross-encoder model optimized for MS Marco passage ranking, offering excellent NDCG@10 (71.01) and MRR@10 (34.85) scores with 4100 docs/sec processing.
