imiraoui/OpenHermes-2.5-Mistral-7B-sharded - Каталог нейросетей
Генерация текста

imiraoui/OpenHermes-2.5-Mistral-7B-sharded

Добавлено:

It allows you to run the model on a free Colab instance / T4 GPU if you load it with quantization. In the tapestry of Greek mythology, Hermes reigns as the eloquent Messenger of the Gods, a deity who deftly bridges the realms through the art of communication. It is in homage to this divine mediator that I name this advanced LLM «Hermes,» a system crafted to navigate the complex intricacies of human discourse with celestial finesse. OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which 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. The code it trained on also improved it’s humaneval score (benchmarking done by Glaive team) from 43% @ Pass 1 with Open Herms 2 to 50.7% @ Pass 1 with Open Hermes 2.5. OpenHermes was trained on 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from…

Модальности:
Генерация текста

Области применения:
Следование инструкциям Диалог / чат


Задача: Генерация текста
Автор: imiraoui
Теги: mistral, instruct, finetune, chatml, gpt4, synthetic data, distillation, conversational
Лайков: 2  |  Загрузок: 12

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.