Generative ai
DeepSeek-R1 is here! ⚡ Performance on par with OpenAI-o1 📖 Fully open-source model & technical report 🏆 MIT licensed: Distill & commercialize freely! ...
Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 1 ...
1. Introduction We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-eff ...
Gemini 2.0 Flash offers a significantly faster time to first token (TTFT) compared to Gemini 1.5 Flash, while maintaining quality on par with larger models like [Gemini 1.5 ...
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported ...
Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge. Crea ...
Mag Mell is a merge of pre-trained language models created using mergekit, based on Mistral Nemo. It is a great roleplay and storytelling model which combines the best part ...
Gemini 2.0 Flash Thinking Mode is an experimental model that's trained to generate the "thinking process" the model goes through as part of its response. As a result, Thinking Mode is capable of stro ...
EVA Llama 3.33 70b is a roleplay and storywriting specialist model. It is a full-parameter finetune of Llama-3.3-70B-Instruct on mixture of ...
Euryale L3.3 70B is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.2. ...
Experimental release (December 6, 2024) of Gemini. ...
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimiz ...
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthro ...
Google's latest multimodal model, supporting image and video in text or chat prompts. Optimized for language tasks including:Code generation Text generation Text editing Problem solving...
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https ...
A wild 7B parameter model that merges several models using the new task_arithmetic merge method from mergekit. List of merged models:NousResearch/Nous-Capybara-7B-V1.9 [HuggingFaceH4/zephyr-7b-b...
A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge ...
GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more afford ...
GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more afford ...
One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge _These are extended-context endpoints for [MythoMax 13B](/gryphe/mythomax-l2-13b ...
One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge _These are extended-context endpoints for [MythoMax 13B](/gryphe/mythomax-l2-13b ...
A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge ...
PaLM 2 fine-tuned for chatbot conversations that help with code-related questions. ...
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch anno ...
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch anno ...
Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance. This is a normal offline LLM, but the [online version](/perpl ...
Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance. This is a normal offline LLM, but the [online version](/perpl ...
OpenChat 7B is a library of open-source language models, fine-tuned with "C-RLFT (Conditioned Reinforcement Learning Fine-Tuning)" - a strategy inspired by offline reinforcement learning. It has been ...
An older GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Sep 2021. ...
A wild 7B parameter model that merges several models using the new task_arithmetic merge method from mergekit. List of merged models:NousResearch/Nous-Capybara-7B-V1.9 [HuggingFaceH4/zephyr-7b-b...
A pretrained generative Sparse Mixture of Experts, by Mistral AI. Incorporates 8 experts (feed-forward networks) for a total of 47B parameters. Base model (not fine-tuned for instructions) - see [Mix ...
This model is currently powered by Mistral-7B-v0.2, and incorporates a "better" fine-tuning than Mistral 7B, inspired by community work. It's best used for larg ...
Google's flagship text generation model. Designed to handle natural language tasks, multiturn text and code chat, and code generation. See the benchmarks and prompting guidelines from [Deepmind](htt ...
The NeverSleep team is back, with a Llama 3 70B finetune trained on their curated roleplay data. Striking a balance between eRP and RP, Lumimaid was designed to be serious, yet uncensored when necess ...
A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to@chargoddard for developing the fr...
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coher ...
WizardLM-2 7B is the smaller variant of Microsoft AI's latest Wizard model. It is the fastest and achieves comparable performance with existing 10x larger opensource leading models It is a finetune ...
Google's latest multimodal model, supporting image and video in text or chat prompts. Optimized for language tasks including:Code generation Text generation Text editing Problem solving...
DBRX is a new open source large language model developed by Databricks. At 132B, it outperforms existing open source LLMs like Llama 2 70B and Mixtral-8x7b on standard indu ...
Euryale 70B v2.1 is a model focused on creative roleplay from Sao10k.Better prompt adherence. Better anatomy / spatial awareness. Adapts much better to unique and...
A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. *Mistral 7B Instruct has multiple version variants, and this is intended to be the latest ...
Command is an instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models. Use of this model is ...
Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows ...
Qwen2 7B is a transformer-based model that excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning. It features SwiGLU activation, attention QKV bias, and gro ...
Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of text generation ...
From the maker of Goliath, Magnum 72B is the first in a new family of models designed to achieve the prose quality of the Claude 3 models, notably Opus ...
A 7.3B parameter Mamba-based model designed for code and reasoning tasks.Linear time inference, allowing for theoretically infinite sequence lengths 256k token context window Optimized for qu...
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chi ...
Qwen2 7B is a transformer-based model that excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning. It features SwiGLU activation, attention QKV bias, and gro ...
The first image to text model from Mistral AI. Its weight was launched via torrent per their tradition: https://x.com/mistralai/status/1833758285167722836 ...
Phi-3.5 models are lightweight, state-of-the-art open models. These models were trained with Phi-3 datasets that include both synthetic data and the filtered, publicly available websites data, with a ...
Dynamic model continuously updated to the current version of GPT-4o in ChatGPT. Intended for research and evaluation. Note: This model is currently experimental and not suitable fo ...
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This is the base 405B pre-trained version. It has demonstrated strong performance compared to leading closed-sour ...
Google's latest multimodal model, supporting image and video in text or chat prompts. Optimized for language tasks including:Code generation Text generation Text editing Problem solving...
Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding. See the launch announcement and benchmark result ...
Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments. See the launch announcement and ...
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https: ...
Jamba 1.5 Large is part of AI21's new family of open models, offering superior speed, efficiency, and quality. It features a 256K effective context window, the longest among open models, enabling im ...
Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1. ...
Jamba 1.5 Mini is the world's first production-grade Mamba-based model, combining SSM and Transformer architectures for a 256K context window and high efficiency. It works with 9 languages and can h ...
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning ...
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context cohere ...
Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question answ ...
Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question answ ...
Lumimaid v0.2 8B is a finetune of Llama 3.1 8B with a "HUGE step up dataset wise" compared to Lumimaid v0.1. Sloppy chats output were purged. Usage of this model ...
GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more afford ...
Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines For emotional intelligence similar to Pi, ...
Liquid's 40.3B Mixture of Experts (MoE) model. Liquid Foundation Models (LFMs) are large neural networks built with computational units rooted in dynamic systems. LFMs are general-purpose AI models ...
Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:Significantly more knowledge and has greatly improved capabilities in coding an...
Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported:Expanded vocabulary with unique and expressive word choices Enhanced creativity for vivid narrati...
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with ...
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with ...
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:Significantly more knowledge and has greatly improved capabilities in coding a...
The Llama 90B Vision model is a top-tier, 90-billion-parameter multimodal model designed for the most challenging visual reasoning and language tasks. It offers unparalleled accuracy in image caption ...
Experimental release (November 21st, 2024) of Gemini. ...
An experimental version of Gemini 1.5 Pro from Google. ...
Mistral Large 2 2411 is an update of Mistral Large 2 released together with Pixtral Large 2411 It is fluent in English, Fren ...
ERNIE Bot Overview Key Capabilities and Use Cases:Engages in interactive dialogues, answers questions, and assists with creative tasks. Facilitates efficient information ret...
Developer/Company: Baidu Overview: ERNIE Bot Turbo is an enhanced version of ERNIE Bot, offering expanded capabilities with support for 7K input + 1K output. It includes system ...
Developer/Company: Baidu Research Key Capabilities & Use Cases: ERNIE-4.0-8K is valuable in natural language processing (NLP), applicable to search engines, intelligent custome ...
Basic Information The "GLM-4-AIRX" is an advanced large language model developed by experts in the field of artificial intelligence. It is renowned for its powerful natural language ...
GLM-4-Flash Model Introduction Key Capabilities and Primary Use CasesHandles multi-turn dialogues, web searches, and tool calls. Supports long text inference with a context...
GLM-4V-Plus Model Introduction Key Capabilities and Primary Use CasesMultimodal Understanding: Excels in image and video understanding, including temporal sequence analys...
GLM-4-Plus Model Introduction Key Capabilities and Primary Use CasesLanguage Understanding: Advanced capabilities in language comprehension, instruction following, and lo...
GLM-4 Long GLM-4 Long is a state-of-the-art language model designed for extended context processing, making it ideal for applications requiring comprehensive text analysis and genera ...
GLM-4 Air Model Introduction Key Capabilities and Primary Use CasesMultilingual Support: Primarily aligned for Chinese and English, with additional support for 24 languag...
Inferor is a merge of top roleplay models, expert on immersive narratives and storytelling. This model was merged using the Model Stock merge method ...
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:Signifi...
SorcererLM is an advanced RP and storytelling model, built as a Low-rank 16-bit LoRA fine-tuned on WizardLM-2-8x22B.Advanced reasoning and emotional intelligence for engaging and im...
A roleplaying/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it ...
UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios. ...
Lumimaid v0.2 70B is a finetune of Llama 3.1 70B with a "HUGE step up dataset wise" compared to Lumimaid v0.1. Sloppy chats output were purged. Us ...
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. The model is fine-tuned on top of [Qwen2.5 72B]. ...
Grok Beta is xAI's experimental language model with state-of-the-art reasoning capabilities, best for complex and multi-step use cases. It is the successor of [Grok 2](https://x.ai/blo ...
Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mi ...
Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up ...
NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging Llama 3.1 70B architect ...
Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines For emotional intelligence s ...
A model specializing in RP and creative writing, this model is based on Qwen2.5-14B, fine-tuned with a mixture of synthetic and natural data. It is trained on 1.5M tokens of role-play ...
Liquid's 40.3B Mixture of Experts (MoE) model. Liquid Foundation Models (LFMs) are large neural networks built with computational units rooted in dynamic systems. LFMs are general-purp ...
From the maker of Goliath, Magnum 72B is the seventh in a family of models designed to achieve the prose quality of the Claude 3 models, ...
Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported:Expanded vocabulary with unique and expressive word choices Enhanced creativity for...
Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual ...
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its small ...
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. ...
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. ...
The Llama 90B Vision model is a top-tier, 90-billion-parameter multimodal model designed for the most challenging visual reasoning and language tasks. It offers unparalleled accuracy in ...
The Llama 90B Vision model is a top-tier, 90-billion-parameter multimodal model designed for the most challenging visual reasoning and language tasks. It offers unparalleled accuracy in ...
The first image to text model from Mistral AI. Its weight was launched via torrent per their tradition: https://x.com/mistralai/status/1833758285167722836 ...
command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version ...
command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is be ...
Gemini 1.5 Flash 8B Experimental is an experimental, 8B parameter version of the Gemini 1.5 Flash model. Usage of Gemini is subject to Google's [Gemini Term ...
Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1. ...
Qwen2 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements:SoTA understanding of images of various resolution & ratio: Qwen2-VL achieves state-of-the-art...
Jamba 1.5 Large is part of AI21's new family of open models, offering superior speed, efficiency, and quality. It features a 256K effective context window, the longest among open model ...
Phi-3.5 models are lightweight, state-of-the-art open models. These models were trained with Phi-3 datasets that include both synthetic data and the filtered, publicly available website ...
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplay ...
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long ...
Dynamic model continuously updated to the current version of GPT-4o in ChatGPT. Intended for research and evaluation. Note: This model is currently experimental and n ...
Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance. The model is built upon the Llama 3.1 405B and h ...
Starcannon 12B is a creative roleplay and story writing model, using nothingiisreal/mn-celeste-12b as a base and [intervitens/mini ...
Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance. This is the online version of the [offline chat ...
Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance. This is the online version of the [offline chat ...
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrate ...
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compar ...
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, P ...
Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of t ...
Dolphin 2.9 is designed for instruction following, conversational, and coding. This model is a finetune of Mixtral 8x22B Instruct. It features a 64k ...
A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. *Mistral 7B Instruct has multiple version variants, and this is intended to ...
A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. *Mistral 7B Instruct has multiple version variants, and this is intended to ...
Phi-3 Mini is a powerful 3.8B parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference ...
Phi-3 128K Medium is a powerful 14-billion parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning a ...
Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its siz ...
WizardLM-2 7B is the smaller variant of Microsoft AI's latest Wizard model. It is the fastest and achieves comparable performance with existing 10x larger opensource leading models It ...
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all ...
Google's latest multimodal model, supporting image and video in text or chat prompts. Optimized for language tasks including:Code generation Text generation Text editing Prob...
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results ...
Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding. See the launch announcement and be ...
This model is currently powered by Mistral-7B-v0.2, and incorporates a "better" fine-tuning than Mistral 7B, inspired by community work. It's best ...
This is a 16k context fine-tune of Mixtral-8x7b. It excels in coding tasks due to extensive training with coding data and is known for its obedience, although ...
Google's flagship multimodal model, supporting image and video in text or chat prompts for a text or code response. See the benchmarks and prompting guidelines from [Deepmind](https:// ...
A pretrained generative Sparse Mixture of Experts, by Mistral AI. Incorporates 8 experts (feed-forward networks) for a total of 47B parameters. Base model (not fine-tuned for instructio ...
OpenChat 7B is a library of open-source language models, fine-tuned with "C-RLFT (Conditioned Reinforcement Learning Fine-Tuning)" - a strategy inspired by offline reinforcement learnin ...
OpenChat 7B is a library of open-source language models, fine-tuned with "C-RLFT (Conditioned Reinforcement Learning Fine-Tuning)" - a strategy inspired by offline reinforcement learnin ...
A Mythomax/MLewd_13B-style merge of selected 70B models. A multi-model merge of several LLaMA2 70B finetunes for roleplaying and creative work. The goal was to create a model that combi ...
A wild 7B parameter model that merges several models using the new task_arithmetic merge method from mergekit. List of merged models:NousResearch/Nous-Capybara-7B-V1.9 [HuggingFace...
A wild 7B parameter model that merges several models using the new task_arithmetic merge method from mergekit. List of merged models:NousResearch/Nous-Capybara-7B-V1.9 [HuggingFace...
PaLM 2 is a language model by Google with improved multilingual, reasoning and coding capabilities. ...
PaLM 2 fine-tuned for chatbot conversations that help with code-related questions. ...
This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021. ...
A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge ...
A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge _These are extended-context endpoints for ReMM SLERP 13B. They may have ...
One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge ...