- MythoMist 7B
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.
#mergeby gryphe33k context$0.00/M input tkns$0.00/M output tkns73.6M tokens this week
- OpenHermes 2.5 Mistral 7B
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.by teknium4k context$0.20/M input tkns$0.20/M output tkns242.3M tokens this week
- OpenHermes 2 Mistral 7B
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.by teknium4k context$0.20/M input tkns$0.20/M output tkns112.9M tokens this week
- Nous: Hermes 70B
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.by nousresearch4k context$0.90/M input tkns$0.90/M output tkns10.7M tokens this week
- Nous: Hermes 13B
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.by nousresearch4k context$0.15/M input tkns$0.15/M output tkns117.9M tokens this week