aiplanet/effi-13b-quant - Каталог нейросетей
Генерация текста

aiplanet/effi-13b-quant

Добавлено:

LlaMa-2 13b fine-tuned on the kaist-ai/CoT-Collection dataset by using the method QLoRA in 4-bit with PEFT library. Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Model Architecture Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety The following bitsandbytes quantization config was used during training: — bits: 4 — groupsize: 128 — dataset: «c4» — descact: False — tokenizer:tokeniaer — device_map: «auto»

Модальности:
Генерация текста

Области применения:
Генерация кода


Задача: Генерация текста
Автор: aiplanet
Теги: llama, generated_from_trainer, code, coding, llama-2, endpoints_compatible, 4-bit, gptq
Лайков: 2  |  Загрузок: 4

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.