IconicAI/NeuralHermes-2.5-Mistral-7B-exl2-5bpw - Каталог нейросетей
Генерация текста

IconicAI/NeuralHermes-2.5-Mistral-7B-exl2-5bpw

Добавлено:

EXL2 quantisation of NeuralHermes-2.5-Mistral-7B, for use with ExLLamaV2. Model size: 4.6GB (3x reduction), 5 bits-per-weight average, 6bpw on head. Command: python convert.py -i convert/NeuralHermes-2.5-Mistral-7B -c convert/0000.parquet -o convert/temp2 -cf convert/nh-5bpw -b 5.0 -hb 6 Layer measurements are provided in measurement.json for further quantisation. NeuralHermes is an OpenHermes-2.5-Mistral-7B model that has been further fine-tuned with Direct Preference Optimization (DPO) using the mlabonne/chatmldpopairs dataset. It is directly inspired by the RLHF process described by neural-chat-7b-v3-1’s authors to improve performance. I used the same dataset and reformatted it to apply the ChatML template. I haven’t performed a comprehensive evaluation of the model, but it works great, nothing broken apparently! 🙂 The code to train this model is available on Google Colab and GitHub. It required an A100 GPU for about an hour. GGUF versions of this model are available here: mlabonne/NeuralHermes-2.5-Mistral-7B-GGUF. You can run this model using LM Studio or any other frontend. LoRA: r=16, loraalpha=16, loradropout=0.05, bias=»none», tasktype=»CAUSALLM», …

Модальности:
Генерация текста

Области применения:
Следование инструкциям Диалог / чат


Задача: Генерация текста
Автор: IconicAI
Теги: mistral, instruct, finetune, chatml, gpt4, synthetic data, distillation, dpo
Лайков: 2  |  Загрузок: 11

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.