Brief-details: SQLCoder is a 15B parameter LLM specialized in SQL query generation, outperforming GPT-3.5-turbo with 64.6% accuracy on novel datasets. Built on StarCoder base.
Brief Details: CodeQwen1.5-7B-Chat is a powerful 7.25B parameter code-specific LLM supporting 92 programming languages with 64K context length and specialized code generation capabilities.
Brief-details: Yi-34B-200K is a powerful bilingual LLM with 34.4B parameters, featuring extended 200K context window and state-of-the-art performance in benchmarks like MMLU and C-Eval.
Brief Details: A specialized text-to-image negative embedding model for Stable Diffusion that helps improve image quality by defining what not to generate
Brief Details: XGen-7B-8K-Base is Salesforce's 7B parameter LLM optimized for 8K sequence lengths, featuring Apache 2.0 license and tiktoken tokenization.
BRIEF-DETAILS: 4-bit quantized 13B parameter Wizard-Vicuna model optimized for unrestricted text generation, featuring GPTQ compression and multiple branch options
Brief-details: A powerful 34B parameter code generation model fine-tuned from CodeLlama, achieving 67.6% pass@1 on HumanEval, matching GPT-4's performance. Trained on 80k programming problems.
BRIEF-DETAILS: A specialized Stable Diffusion model fine-tuned on Elden Ring game art, enabling generation of fantasy artwork in the distinctive Elden Ring style.
I apologize, but I want to note that I should avoid generating details that could promote NSFW content. I'll focus on the technical aspects while keeping the content appropriate. Brief Details: A LoRA extension for FLUX.1-dev model, focused on text-to-image generation using diffusers library. Built by enhanceaiteam with 320 likes
Brief-details: A 1.1B parameter code generation model trained on Python, Java & JavaScript, featuring Fill-in-the-Middle capabilities and Multi-Query Attention architecture.
Brief-details: A 7B parameter math LLM specialized in solving complex mathematical problems using tool-integrated reasoning, achieving state-of-the-art performance on various math benchmarks.
Brief-details: Specialized 70B parameter LLaMA3-based model optimized for conversational QA and RAG, outperforming GPT-4 on multiple benchmarks.
Brief Details: A 7B parameter LLM fine-tuned with RLAIF, based on Mistral-7B and OpenChat. Scores 8.12 on MT Bench, optimized for helpful responses.
Brief Details: OpenELM-3B-Instruct is a 3B parameter instruction-tuned language model by Apple, featuring efficient parameter allocation and strong zero-shot performance.
Brief-details: MPT-30B is a 30B parameter decoder-style transformer trained on 1T tokens, featuring 8k context window, FlashAttention, and ALiBi position encoding.
Brief Details: Qwen-72B is a powerful 72B parameter LLM supporting 32k context, trained on 3T+ tokens with multilingual capabilities and state-of-the-art performance across benchmarks
Brief-details: A powerful 34B parameter bilingual chat model from 01.ai, ranking 2nd on AlpacaEval after GPT-4 Turbo, with superior performance in reasoning and comprehension.
Brief Details: Spider-Verse Diffusion - A fine-tuned Stable Diffusion model creating Into the Spider-Verse movie style images using "spiderverse style" token. 343 likes, 579 downloads.
Brief Details: A powerful 479B parameter MoE-based LLM from Snowflake combining dense and sparse architectures, optimized for enterprise use with Apache 2.0 license.
Brief-details: A photorealistic AI image generation model built on Stable Diffusion v1-5, featuring granular adaptive learning and specialized trigger words for enhanced artistic control
Brief-details: Qwen-14B-Chat is a powerful 14B parameter multilingual LLM optimized for Chinese/English, featuring advanced capabilities in coding, math, and tool usage with strong performance on benchmarks.
