Novita

Specialized in Next.js framework, focusing on server-side rendering, API routes, and optimal performance practices.

Novita Python Assistant

Airoboros-L2-70B fine-tunes Llama-2-70B for extended creative writing and narrative generation. This model specializes in chapter continuations, character dialogues, and multi-participant storytelling scenarios.

DeepSeek R1 Distill LLama 70B

DeepSeek R1 Distill Qwen 14B leverages Qwen 2.5 and DeepSeek R1 for superior performance. This 14B distilled model outperforms OpenAI's o1-mini, scoring 74% on MMLU and excelling in math tasks (AIME: 69.7%, MATH-500: 93.9%)

DeepSeek R1 Distill Qwen 32B distils Qwen 2.5 and DeepSeek R1 expertise into a powerful 32B model. Outperforms OpenAI's o1-mini with impressive math capabilities (AIME: 72.6%, MATH-500: 94.3%) and coding skills (CodeForces: 1691).

Dolphin-Mixtral-8x22B fine-tunes Mixtral's MoE architecture with 64k context length. This model enhances instruction following, conversation, and coding capabilities while requiring external alignment for deployment.

Gemma-2-9B-IT is Google's instruction-tuned lightweight model based on Gemini technology. This 9B parameter decoder-only model balances performance with efficiency for diverse text-generation tasks.

Hermes-2-Pro-Llama-3-8B fine-tunes Llama-3-8B with the enhanced OpenHermes 2.5 dataset. This 8B model specializes in function calling and structured JSON outputs while maintaining strong general capabilities.

L31-70B-Euryale-v2.2 builds on its predecessor using Llama-3.1-70B as a base. This iteration by Sao10k enhances creative writing and character interaction capabilities.

L3-70B-Euryale-v2.1 is a creative writing model based on Llama-3-70B, optimized for narrative generation and character interactions. This 70B parameter model focuses on imaginative storytelling and dynamic dialogue.

L3-8B-Lunaris merges Llama-3-8B variants for general tasks and creative roleplay. This 8B parameter model by Sao10K balances broad capabilities with narrative generation.

L3-8B-Stheno-v3.2 is an 8B parameter model optimized for dynamic role-play and character immersion. This specialized model focuses on consistent character portrayal and contextual responses.

Meta's Llama 3.1 70B-instruct model excels in multilingual dialogue and complex reasoning. This instruction-tuned powerhouse sits between the efficient 8B and massive 405B variants, offering optimal performance-to-size ratio and outperforming many closed-source competitors.

Meta's latest class of models, Llama 3.1, launched with a variety of sizes and configurations. The 8B instruct-tuned version is particularly fast and efficient. It has demonstrated strong performance in human evaluations, outperforming several leading closed-source models.

Llama-3.1-8B-Instruct-BF16 optimizes the 8B architecture with bfloat16 precision. This instruction-tuned model balances efficiency and performance, showing competitive results against larger closed-source alternatives.

Llama-3.2-11B-Vision-Instruct combines visual and language processing at 11B parameters. This multimodal model excels in image captioning, visual QA, and complex image analysis through integrated visual-linguistic understanding.

Llama-3.2-1B-Instruct is Meta's compact multilingual model at 1B parameters. This instruction-tuned version balances efficiency with generative capabilities across multiple languages.

Llama-3.2-3B-Instruct is Meta's medium-sized multilingual model at 3B parameters. This instruction-tuned version offers enhanced generative capabilities while maintaining efficient deployment.

Offers similar performance compared to the Llama 3.1 70B model

Llama-3-70B-Instruct is Meta's instruction-tuned model at 70B parameters, trained on 15T tokens. This decoder-only architecture shows competitive dialogue performance against leading closed-source models.

Llama-3-8B-Instruct is Meta's compact dialogue model with 8B parameters, trained on 15T tokens. This instruction-tuned decoder demonstrates competitive performance against larger closed-source models in human evaluations.

Midnight-Rose-70B merges multiple models for advanced creative writing and storytelling. This 70B parameter model builds on Rogue Rose and Aurora Nights, optimizing for detailed narrative generation and character interactions.

Mistral-7B-Instruct fine-tunes the base Mistral-7B for instruction following. This 7.3B parameter model optimizes speed and context length while maintaining strong performance across diverse tasks.

Mistral-Nemo combines NVIDIA collaboration with impressive 128k context in a 12B package. This Apache-licensed model supports 11 languages and function calling, while outperforming similarly-sized competitors.

MythoMax L2 13B combines MythoLogic-L2's comprehension with Huginn's writing capabilities through innovative tensor merging. This 13B hybrid model balances robust understanding with creative expression.

Nous-Hermes-Llama2-13B fine-tunes Llama-2-13B on 300K curated instructions. This collaborative effort between Nous Research, Teknium, and Emozilla optimizes instruction-following capabilities.

OpenChat-7B uses C-RLFT (Conditioned Reinforcement Learning Fine-Tuning) to enhance a 7B parameter base model. This innovative approach trains on mixed-quality data without requiring preference labels.

OpenHermes-2.5-Mistral-7B enhances the Mistral-7B base model with specialized code training. This iteration builds on OpenHermes 2's foundation while expanding programming capabilities.

Qwen-2.5-72B-Instruct leads the Qwen2.5 series at 72B parameters. This instruction-tuned transformer excels in language understanding, coding, mathematics, reasoning, and multilingual tasks.

Qwen-2-7B-Instruct is a 7B parameter transformer optimized for diverse tasks. This instruction-tuned model excels in language understanding, coding, mathematics, reasoning, and multilingual support.

Qwen-2-VL-72B-Instruct is a multimodal model handling images, videos, and text across languages. This 72B parameter model excels in visual analysis, 20+ minute video understanding, device control, and multilingual text recognition.

WizardLM-2 8x22B is Microsoft's latest Mixture-of-Experts model, using 8 expert networks of 22B parameters each. This 176B total parameter architecture delivers competitive performance in knowledge-intensive tasks.