**Brief Details:** Anime-focused text-to-image diffusion model, fine-tuned for high-quality anime art generation. Created by hakurei with 1110+ likes and CreativeML OpenRAIL-M license.
Brief-details: Yi-34B is a powerful bilingual LLM with 34.4B parameters, outperforming many larger models in benchmarks. Apache 2.0 licensed, strong at reasoning and comprehension.
Brief Details: Improved VAE model for Stable Diffusion with MSE-focused fine-tuning, offering smoother outputs and better reconstruction quality compared to original VAE.
Brief Details: OmniParser - Microsoft's screenshot parsing tool that converts UI elements to structured format using YOLOv8 and BLIP-2, ideal for GUI agents.
Brief-details: GOT-OCR2_0 is a 716M parameter multilingual OCR model supporting plain text, formatted text, and fine-grained recognition with advanced vision-language capabilities.
Brief-details: A 70B parameter LLM based on Llama 3.1, featuring innovative Reflection-Tuning for self-correction and improved reasoning capabilities.
Brief-details: ChatTTS is a text-to-speech AI model with 7.9K+ downloads, offering batch processing capabilities and customizable speech parameters including speaker selection and speed control.
Brief-details: OpenELM is Apple's efficient language model family with sizes from 270M to 3B parameters, featuring layer-wise scaling for enhanced accuracy
Brief-details: A comprehensive collection of community-created SD control models, pre-converted to float16 and safetensor format for flexible integration.
Brief-details: Databricks' 12B parameter instruction-following LLM based on Pythia-12b, trained on 15k instruction/response records, MIT licensed for commercial use.
Brief-details: ChatGLM2-6B is an advanced bilingual LLM with 6B parameters, featuring enhanced context length (32K), faster inference, and strong performance across multiple benchmarks.
Brief-details: Anime-focused text-to-image diffusion model fine-tuned on high-quality anime images. Popular with 9K+ downloads, supports Stable Diffusion pipeline for generating anime-style artwork.
Brief-details: Stable Diffusion v1.4 is a powerful text-to-image latent diffusion model trained on LAION-5B dataset, capable of generating photorealistic images from text prompts at 512x512 resolution.
BRIEF-DETAILS: Grok-1: A 314B parameter open-weights language model by xAI, featuring Apache 2.0 license and specialized text generation capabilities
Brief Details: ChatGLM-6B is a 6.2B parameter bilingual LLM optimized for Chinese-English dialogue, featuring efficient quantization for 6GB GPU deployment
Brief-details: Versatile anime-style image generation model collection featuring realistic textures and detailed anatomy. Multiple variants for different art styles, from SFW to NSFW content.
Brief-details: NorBERT 3 base - A 123M parameter Norwegian language model supporting both Bokmål and Nynorsk, built for masked language modeling and various NLP tasks.
Brief-details: BLOOM - A 176B parameter open-source multilingual language model supporting 46 languages and 13 programming languages. First-of-its-kind large language model trained openly and collaboratively.
Brief Details: RoBERTa-based emotion classification model trained on Twitter data, supporting multilabel emotion detection with high F1 scores (micro: 0.7169, macro: 0.5464).
Brief Details: PetBERT - A 108M parameter BERT-based model trained on 500M+ veterinary clinical records for enhanced animal disease surveillance and diagnosis
BRIEF DETAILS: A Turkish BERT model fine-tuned for question answering on TQuAD2 dataset, achieving 2.0776 validation loss after 3 epochs of training with MIT license.
