LLM Rankings

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. • 8192 context

A #merge model based on [Llama-2-13B](/models/meta-llama/llama-2-13b-chat) and made possible thanks to the compute provided by the KoboldAI community. It's a merge between: - [KoboldAI/LLaMA2-13B-Tiefighter](https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter) - [chaoyi-wu/MedLLaMA_13B](https://huggingface.co/chaoyi-wu/MedLLaMA_13B) - [Doctor-Shotgun/llama-2-13b-chat-limarp-v2-merged](https://huggingface.co/Doctor-Shotgun/llama-2-13b-chat-limarp-v2-merged). #merge • 4096 context

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text. • 9000 context

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text. • 100000 context

A continuation of [OpenHermes 2 model](/models/teknium/openhermes-2-mistral-7b), 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. • 4096 context

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. • 16385 context

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. • 4095 context

From the creator of [MythoMax](/models/gryphe/mythomax-l2-13b), merges a suite of models to reduce word anticipation, ministrations, and other undesirable words in ChatGPT roleplaying data. It combines [Neural Chat 7B](/models/intel/neural-chat-7b), Airoboros 7b, [Toppy M 7B](/models/undi95/toppy-m-7b), [Zepher 7b beta](/models/huggingfaceh4/zephyr-7b-beta), [Nous Capybara 34B](/models/nousresearch/nous-capybara-34b), [OpenHeremes 2.5](/models/teknium/openhermes-2.5-mistral-7b), and many others. #merge • 32768 context

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. • 16385 context

Ability to understand images, in addition to all other [GPT-4 Turbo capabilties](/models/openai/gpt-4-1106-preview). Training data: up to Apr 2023. **Note:** heavily rate limited by OpenAI while in preview. • 128000 context

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. • 4095 context

A collab between IkariDev and Undi. This merge is suitable for RP, ERP, and general knowledge. #merge • 8192 context

PaLM 2 fine-tuned for chatbot conversations that help with code-related questions. • 7168 context

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text. • 100000 context

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. • 8192 context

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. • 32000 context

Anthropic's model for low-latency, high throughput text generation. Supports up to 100k tokens in one pass, or hundreds of pages of text. • 100000 context

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. • 8191 context

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. • 4095 context

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](/models/huggingfaceh4/zephyr-7b-beta) - lemonilia/AshhLimaRP-Mistral-7B - Vulkane/120-Days-of-Sodom-LoRA-Mistral-7b - Undi95/Mistral-pippa-sharegpt-7b-qlora #merge • 32768 context