Dracones/c4ai-command-r-v01_exl2_6.0bpw

This is a 6.0bpw EXL2 quant of CohereForAI/c4ai-command-r-v01 Details about the model can be found at the above model page. These quants were made with exllamav2 version 0.0.18. Quants made on this version of EXL2 may not work on older versions of the exllamav2 library. If you have problems loading these models, please update Text Generation WebUI to the latest version. The rpcal quants were made using data/PIPPA-cleaned/pipparawfix.parquet for calibration. Below are the perplexity scores for the EXL2 models. A lower score is better. Here are the EQ Bench scores for the EXL2 quants using Alpaca, ChatML, Command-R and Command-R-Plus prompt templates. A higher score is better. This is the Command-R-Plus template yaml that was used in EQ bench(which uses Text Generation Web UI yaml templates). It adds BOS_TOKEN into the starter prompt. text-generation-webui/instruction-templates/Command-R-Plus.yaml:

Модальности:
Генерация текста

Задача: Генерация текста
Автор: Dracones
Теги: cohere, exl2, en, fr, de, es, it, pt
Лайков: 3  |  Загрузок: 30

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.