The larger, internet-connected chat model by Perplexity Labs, based on Llama 2 70B. The online models are focused on delivering helpful, up-to-date, and factual responses. #online

The smaller, internet-connected chat model by Perplexity Labs, based on Mistral 7B. The online models are focused on delivering helpful, up-to-date, and factual responses. #online

The smaller chat model by Perplexity Labs, with 7 billion parameters. Based on Mistral 7B.

The larger chat model by Perplexity Labs, with 70 billion parameters. Based on Llama 2 70B.

A #merge model based on Llama-2-13B and made possible thanks to the compute provided by the KoboldAI community. It's a merge between:

• KoboldAI/LLaMA2-13B-Tiefighter
• chaoyi-wu/MedLLaMA_13B
• Doctor-Shotgun/llama-2-13b-chat-limarp-v2-merged.

#merge

OpenChat 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 trained on mixed-quality data without preference labels.

From the creator of MythoMax, merges a suite of models to reduce word anticipation, ministrations, and other undesirable words in ChatGPT roleplaying data.

It combines Neural Chat 7B, Airoboros 7b, Toppy M 7B, Zepher 7b beta, Nous Capybara 34B, OpenHeremes 2.5, and many others.

#merge

A collab between IkariDev and Undi. This merge is suitable for RP, ERP, and general knowledge. #merge

A fine-tuned model based on mistralai/Mistral-7B-v0.1 on the open source dataset Open-Orca/SlimOrca, aligned with DPO algorithm. For more details, refer to the blog: The Practice of Supervised Fine-tuning and Direct Preference Optimization on Habana Gaudi2.

Claude 2.1 delivers advancements in key capabilities for enterprises—including an industry-leading 200K token context window, significant reductions in rates of model hallucination, system prompts and new beta feature: tool use.

A continuation of OpenHermes 2 model, trained on additional code datasets. Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant.

LLaVA is a large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding, achieving impressive chat capabilities mimicking GPT-4 and setting a new state-of-the-art accuracy on Science QA

This model is trained on the Yi-34B model for 3 epochs on the Capybara dataset. It's the first 34B Nous model and first 200K context length Nous model.

Note: This endpoint currently supports 32k context.

Ability to understand images, in addition to all other GPT-4 Turbo capabilties. Training data: up to Apr 2023.

Note: heavily rate limited by OpenAI while in preview.

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 combines creativity with intelligence for an enhanced experience.

#merge

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-beta
• lemonilia/AshhLimaRP-Mistral-7B
• Vulkane/120-Days-of-Sodom-LoRA-Mistral-7b
• Undi95/Mistral-pippa-sharegpt-7b-qlora

#merge

A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. #merge

Depending on their size, subject, and complexity, your prompts will be sent to MythoMax 13B, MythoMax 13B 8k or GPT-4 Turbo. To see which model was used, visit Activity.

The latest GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Sep 2021.

The latest GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Apr 2023.

Note: heavily rate limited by OpenAI while in preview.

Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was trained on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO).

PaLM 2 is Google's flagship language model with improved multilingual, reasoning and coding capabilities.

PaLM 2 fine-tuned for chatbot conversations that help with code-related questions.

Trained on 900k instructions, surpasses all previous versions of Hermes 13B and below, and matches 70B on some benchmarks. Hermes 2 has strong multiturn chat skills and system prompt capabilities.

A fine-tune of Mistral using the OpenOrca dataset. First 7B model to beat all other models <30B.

A Llama 2 70B fine-tune using synthetic data (the Airoboros dataset).

One of the highest performing fine-tunes of Llama 2 13B, with rich descriptions and roleplay. Extended to 8k context length. #merge

A state-of-the-art language model fine-tuned on over 300k instructions by Nous Research, with Teknium and Emozilla leading the fine tuning process.

Xwin-LM aims to develop and open-source alignment tech for LLMs. Our first release, built-upon on the Llama2 base models, ranked TOP-1 on AlpacaEval. Notably, it's the first to surpass GPT-4 on this benchmark. The project will be continuously updated.

A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.

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.

SynthIA (Synthetic Intelligent Agent) is a LLama-2 70B model trained on Orca style datasets. It has been fine-tuned for instruction following as well as having long-form conversations.

A blend of the new Pygmalion-13b and MythoMax. #merge

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.

GPT-4-32k is an extended version of GPT-4, with the same capabilities but quadrupled context length, allowing for processing up to 40 pages of text in a single pass. This is particularly beneficial for handling longer content like interacting with PDFs without an external vector database. Training data: up to Sep 2021.

GPT-4-32k is an extended version of GPT-4, with the same capabilities but quadrupled context length, allowing for processing up to 40 pages of text in a single pass. This is particularly beneficial for handling longer content like interacting with PDFs without an external vector database. Training data: up to Sep 2021.

A state-of-the-art language model fine-tuned on over 300k instructions by Nous Research, with Teknium and Emozilla leading the fine tuning process.

A fine-tune of CodeLlama-34B on an internal dataset that helps it exceed GPT-4 on some benchmarks, including HumanEval.

Code Llama is built upon Llama 2 and excels at filling in code, handling extensive input contexts, and folling programming instructions without prior training for various programming tasks.

An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.

Anthropic's flagship model. Superior performance on tasks that require complex reasoning. Supports up to 100k tokens in one pass, or hundreds of pages of text.

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text.

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text.

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text.

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text.

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text.

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text.

A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge

PaLM 2 is Google's flagship language model with improved multilingual, reasoning and coding capabilities.

PaLM 2 fine-tuned for chatbot conversations that help with code-related questions.

One of the highest performing fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

A 13 billion parameter language model from Meta, fine tuned for chat completions

A 70 billion parameter language model from Meta, fine tuned for chat completions.

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data: up to Sep 2021.

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data: up to Sep 2021.

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.

GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.

An InstructGPT model derived from the code-davinci-002 model, designed to follow instructions in prompts to provide detailed responses. Training data: up to Sep 2021.