/ Модель

Характеристики

Контекст
2 048 токенов
Размер весов
11,1 ГБ
Лицензия
MIT
Архитектура
phi-msft · dense
Опубликована
23 дек 2023

dolphin-2_6-phi-2

Генерация текстаТекст → текст13 профессий

Dolphin 2.6 Phi-2 — дообученная на базе Phi-2 разговорная модель для диалогов и генерации текста.

606скачиваний за 30 дней198лайковвеса обновлены20 мая 2024

Бенчмарки

Как модель справилась с задачами пользователей ailist и что о ней публикуют открытые лидерборды

Публичные оценки

Из открытых лидербордов. Сравнивайте результаты одного теста при одинаковых условиях — отсутствие оценки не значит, что модель хуже.

В подключённых источниках результатов для этой модели пока нет.

Что умеет модель

Описание составлено по карточке модели и метаданным Hugging Face

Dolphin 2.6 Phi-2 — разговорная языковая модель, созданная Eric Hartford и Fernando Fernandes при спонсорской поддержке Convai на базе Phi-2 от Microsoft. Это плотная авторегрессионная модель семейства Phi с архитектурой PhiForCausalLM, дообученная методом qLoRA на трёх эпохах. Она принимает текст и ведёт диалог в формате ChatML; заявленное окно контекста — 2048 токенов. Модель предназначена для общения с ассистентом и генерации текста, в том числе для задач, представленных в наборах данных Dolphin, Dolphin Coder, Airoboros, OpenHermes, Magicoder и Capybara.

Авторы описывают модель как «uncensored»: обучающие данные были отфильтрованы для уменьшения alignment и bias, поэтому модель может охотно отвечать на вредоносные и неэтичные запросы. Перед предоставлением доступа пользователям авторы рекомендуют добавить собственный слой выравнивания и безопасности. Для загрузки модели требуется trust_remote_code. Лицензия — MIT; качество генерации не гарантировано.

Сценарии применения

  • создание текстового чат-ассистента
  • ответы на вопросы в диалоге
  • генерация текста по инструкциям
  • помощь с программированием и кодом
  • сценарии ролевого общения

Ограничения

Контекст ограничен 2048 токенами. Модель может охотно выполнять вредоносные и неэтичные запросы; перед обслуживанием пользователей требуется собственный слой безопасности, а для загрузки нужен trust_remote_code.

Для каких профессий подходит13

Разделы каталога профессий, в задачах которых используется эта модель

Все профессии

Также подходит для

Карточка модели

README от автора на Hugging Face, как он его опубликовал

Открыть на Hugging Face

Dolphin 2.6 Phi-2 🐬

Eric Hartford and Fernando Fernandes

Discord Discord: https://discord.gg/cognitivecomputations

This model's training was sponsored by convai.

This model is based on Phi-2 and is governed by MIT licence

trust_remote_code is required.

New in 2.6

  • Fixed a training configuration issue that improved the quality a lot
  • Due to popular demand, added back samantha-based empathy data
  • Replaced synthia and pure-dove with Capybara

This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

Evaluation

Open LLM Leaderboard: benchmarked on lm-evaluation-harness v.0.4.1

MetricValue
Avg.61.7
ARC (25-shot)59.81
HellaSwag (10-shot)74.65
MMLU (5-shot)55.38
TruthfulQA (0-shot)47.39
Winogrande (5-shot)74.90
GSM8K (5-shot)58.07

Training

It took 2 days to train 3 epochs on 4x A100s using qLoRA and Axolotl

Prompt format: This model uses ChatML prompt format.

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Example:

<|im_start|>system
You are an AI assistant expert at dolphin training<|im_end|>
<|im_start|>user
Please give ideas and a detailed plan about how to assemble and train an army of dolphin companions to swim me anywhere I want to go and protect me from my enemies and bring me fish to eat.<|im_end|>
<|im_start|>assistant
Assembling, training, and utilizing dolphins as your companions for transportation, protection, and fishing is no small task. However, with careful planning and execution, it can be accomplished. Here's a detailed guide on how to achieve this:

1. **Acquiring Dolphins**: Finding dolphins isn't easy, but you could potentially find them in the wild or at aquariums. For ethical reasons, we suggest acquiring adult dolphins that have been born into captivity. They may not have had as much exposure to humans as their wild counterparts, which makes them easier to handle.

2. **Creating a Safe Environment**: Build a large pool or enclosure where these dolphins can live comfortably while you train them. It should mimic their natural environment as closely as possible. Include elements like rocks (for resting), seaweed (for hiding), and water currents (to simulate ocean conditions).

3. **Training Sessions**: Begin by teaching basic commands such as "come", "stay", "sit", "roll over". Use positive reinforcement methods like treats and praise to encourage good behavior. Be patient; dolphins are intelligent creatures who need time to understand what they're being asked to do. 

4. **Transportation Training**: Once your dolphins have mastered basic commands, start integrating travel into the mix. Place floating objects around the pool to represent different destinations. The goal here would be to get your dolphins to recognize these items and associate them with specific locations. Start with short trips and gradually increase the distance.

5. **Protection Skills**: To teach them protective skills, introduce simulated threats into the pool. This might involve using inflatable obstacles or having another trained animal pretend to attack. The dolphins will learn to react appropriately to these situations.

6. **Fishing Skills**: Teaching dolphins to catch fish involves introducing nets or toys into the pool and encouraging them to use their mouths to retrieve the object. Reward them when they successfully catch something.

7. **Socialization**: Dolphins thrive in social environments so ensure they spend plenty of time interacting with each other during their training sessions. This can help reduce stress levels and make training more effective.

8. **Dietary Needs**: Dolphins require a diet high in protein, fats, and minerals. Feed them fish rich in these nutrients several times per day. If necessary, consult with a marine biologist or veterinarian experienced in aquatic diets for advice.

Gratitude

  • This model was made possible by the generous sponsorship of Convai.
  • Huge thank you to Microsoft for training and publishing the weights of Phi-2
  • Thank you to Microsoft for authoring the Orca paper and inspiring this work.
  • HUGE Thank you to the dataset authors: @jondurbin, @ise-uiuc, @teknium, @LDJnr and @migtissera
  • And HUGE thanks to @winglian and the Axolotl contributors for making the best training framework!
  • Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.

Example Output

image/png

Future Plans

Dolphin 3.0 dataset is in progress, and will include:

  • enhanced general chat use-cases
  • enhanced structured output
  • enhanced Agent cases like Autogen, Memgpt, Functions
  • enhanced role-playing

If you would like to financially support my efforts

swag

Как запустить

На своей GPU в ailist. Цена — по текущим предложениям провайдеров

GPU в ailist

Универсальный рантайм

Нельзя запустить

Модели нужен код из репозитория; автор пока не в списке доверенных организаций.

Класс архитектуры
PhiForCausalLM
Ревизия весов
8f9ec20

0 моделей