Характеристики

Размер весов: 263 ГБ
Лицензия: Своя лицензия
Архитектура: dbrx · dense
Базовая модель: dbrx-base
Опубликована: 13 мая 2024

Ссылки

dolphin-2.9.1-dbrx

Генерация текстаТекст → текст15 профессий

Dolphin 2.9.1 DBRX — дообученная на базе DBRX разговорная модель для выполнения инструкций, написания кода и вызова функций.

30скачиваний за 30 дней9лайковвеса обновлены20 мая 2024

Бенчмарки

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

Тесты пользователейпока нет

Никто ещё не опубликовал тест этой модели. Соберите бенчмарк из своих задач — результат появится здесь.

Добавьте модель в бенчмарк
Вместе с другими моделями категории «Текст» — сравнение идёт внутри одной категории.
Опишите свои задачи
Напишите запросы, при необходимости приложите файлы и эталонные ответы.
Запустите и опубликуйте
Модели ответят на каждую задачу, судья оценит ответы. Опубликованный результат появится на этой странице.

Открыть конструктор бенчмарка

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 2.9.1 DBRX — разговорная и инструкционная языковая модель, дообученная Eric Hartford, Lucas Atkins, Fernando Fernandes и командой Cognitive Computations на базе databricks/dbrx-base. Она использует архитектуру DBRX и формат диалога ChatML; базовая модель поддерживает контекст до 32 тысяч токенов, а дообучение проводилось с длиной последовательности 4 тысячи токенов.

Модель предназначена для диалоговых ответов, выполнения инструкций, генерации кода и начальных агентных сценариев, включая вызов функций. Для коммерческого и иного использования README указывает лицензию databricks-open-model-license, а метаданные — лицензию other; условия следует сверять с лицензией репозитория. Модель описана авторами как uncensored и может охотно отвечать на небезопасные запросы, поэтому перед предоставлением пользователям рекомендуется добавить собственный слой фильтрации.

Сценарии применения

ответы на пользовательские инструкции в чате
генерация и объяснение кода
решение математических текстовых задач
вызов функций в диалоговом агенте
ведение диалога по шаблону ChatML

Ограничения

Модель описана авторами как uncensored и может выполнять небезопасные запросы; перед развертыванием для пользователей рекомендуется собственный слой фильтрации. Дообучение использовало последовательности длиной 4 тысячи токенов, хотя базовая модель поддерживает контекст до 32 тысяч токенов.

Для каких профессий подходит15

Разделы каталога профессий, в задачах которых используется эта модель

Все профессии

II.2Разработка и данныеСоздание и понимание программного кодаAI помогает писать, объяснять и связывать программный код с требованиями и существующей системой.20 задач21 443модели II.6Разработка и данныеДокументация и сопровождение разработкиAI помогает поддерживать понятную техническую документацию и ускорять передачу знаний.18 задач38 015моделей II.10Разработка и данныеРазработка и эксплуатация AI/ML-системAI помогает создавать, оценивать, развёртывать и контролировать AI/ML-системы на всём жизненном цикле.30 задач49 000моделей II.8Разработка и данныеИнженерия данных и аналитикаAI помогает готовить надёжные данные и превращать их в понятную аналитику.22 задачи23 488моделей

Также подходит для

Карточка модели

README от автора на Hugging Face, как он его опубликовал

Открыть на Hugging Face

Dolphin 2.9.1 DBRX 🐬

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations

Discord: https://discord.gg/cognitivecomputations

Our appreciation for the sponsors of Dolphin 2.9.1:

Crusoe Cloud - provided excellent on-demand 8xH100 node

This model is based on databricks/dbrx-base, and is governed by databricks-open-model-license

The base model has 32k context, and the full-weight fine-tuning was with 4k sequence length.

This model was trained FFT on parameters selected by Laser Scanner, using ChatML prompt template format.

example:

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

Dolphin-2.9.1 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.

Dolphin is uncensored. We 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 with 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.

Dolphin is licensed according to Meta's Llama license. We grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. Dolphin was trained on data generated from GPT4, among other models.

Evals

image/png

Training

axolotl version: 0.4.0

base_model: /workspace/axolotl/dbrx-checkpoint
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
# load_in_4bit: true
strict: false

# adapter: qlora
# lora_modules_to_save: [embed_tokens, lm_head]

# lora_r: 32
# lora_alpha: 16
# lora_dropout: 0.05
# lora_target_linear: false
# lora_fan_in_fan_out:

datasets:
  - path: /workspace/datasets/dolphin-2.9/dolphin201-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  # - path: /workspace/datasets/dolphin-2.9/Ultrachat200kunfiltered.jsonl
  #   type: sharegpt
  #   conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/dolphin-coder-translate-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/dolphin-coder-codegen-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/not_samantha_norefusals.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/Orca-Math-resort-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/agent_instruct_react_unfiltered.jsonl
    type: sharegpt  
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_instruct_j1s1_3k_unfiltered.jsonl
    type: sharegpt  
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_negative_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_react_10p_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_tflan_cot_30p_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/openhermes200k_unfiltered.jsonl
    type: sharegpt 
    conversation: chatml
  # - path: /workspace/datasets/dolphin-2.9/SystemConversations.jsonl
  #   type: sharegpt
  #   conversation: chatml

chat_template: chatml

unfrozen_parameters:
- ^lm_head.weight$
# ffn.experts.mlp_experts.0.v1 layers
- transformer.blocks.30.ffn.experts.mlp_experts.0.v1
- transformer.blocks.32.ffn.experts.mlp_experts.0.v1
- transformer.blocks.25.ffn.experts.mlp_experts.0.v1
- transformer.blocks.15.ffn.experts.mlp_experts.0.v1
- transformer.blocks.22.ffn.experts.mlp_experts.0.v1
- transformer.blocks.31.ffn.experts.mlp_experts.0.v1
- transformer.blocks.7.ffn.experts.mlp_experts.0.v1
- transformer.blocks.21.ffn.experts.mlp_experts.0.v1
- transformer.blocks.8.ffn.experts.mlp_experts.0.v1
- transformer.blocks.23.ffn.experts.mlp_experts.0.v1
# ffn.experts.mlp_experts.0.w1 layers
- transformer.blocks.7.ffn.experts.mlp_experts.0.w1
- transformer.blocks.8.ffn.experts.mlp_experts.0.w1
- transformer.blocks.30.ffn.experts.mlp_experts.0.w1
- transformer.blocks.4.ffn.experts.mlp_experts.0.w1
- transformer.blocks.0.ffn.experts.mlp_experts.0.w1
- transformer.blocks.32.ffn.experts.mlp_experts.0.w1
- transformer.blocks.6.ffn.experts.mlp_experts.0.w1
- transformer.blocks.3.ffn.experts.mlp_experts.0.w1
- transformer.blocks.25.ffn.experts.mlp_experts.0.w1
- transformer.blocks.5.ffn.experts.mlp_experts.0.w1
# ffn.experts.mlp_experts.0.w2 layers
- transformer.blocks.25.ffn.experts.mlp_experts.0.w2
- transformer.blocks.22.ffn.experts.mlp_experts.0.w2
- transformer.blocks.27.ffn.experts.mlp_experts.0.w2
- transformer.blocks.26.ffn.experts.mlp_experts.0.w2
- transformer.blocks.4.ffn.experts.mlp_experts.0.w2
- transformer.blocks.29.ffn.experts.mlp_experts.0.w2
- transformer.blocks.32.ffn.experts.mlp_experts.0.w2
- transformer.blocks.5.ffn.experts.mlp_experts.0.w2
- transformer.blocks.7.ffn.experts.mlp_experts.0.w2
- transformer.blocks.3.ffn.experts.mlp_experts.0.w2
# ffn.experts.mlp_experts.1.v1 layers
- transformer.blocks.27.ffn.experts.mlp_experts.1.v1
- transformer.blocks.25.ffn.experts.mlp_experts.1.v1
- transformer.blocks.29.ffn.experts.mlp_experts.1.v1
- transformer.blocks.33.ffn.experts.mlp_experts.1.v1
- transformer.blocks.23.ffn.experts.mlp_experts.1.v1
- transformer.blocks.30.ffn.experts.mlp_experts.1.v1
- transformer.blocks.6.ffn.experts.mlp_experts.1.v1
- transformer.blocks.21.ffn.experts.mlp_experts.1.v1
- transformer.blocks.15.ffn.experts.mlp_experts.1.v1
- transformer.blocks.7.ffn.experts.mlp_experts.1.v1
# ffn.experts.mlp_experts.1.w1 layers
- transformer.blocks.0.ffn.experts.mlp_experts.1.w1
- transformer.blocks.6.ffn.experts.mlp_experts.1.w1
- transformer.blocks.7.ffn.experts.mlp_experts.1.w1
- transformer.blocks.4.ffn.experts.mlp_experts.1.w1
- transformer.blocks.8.ffn.experts.mlp_experts.1.w1
- transformer.blocks.29.ffn.experts.mlp_experts.1.w1
- transformer.blocks.33.ffn.experts.mlp_experts.1.w1
- transformer.blocks.27.ffn.experts.mlp_experts.1.w1
- transformer.blocks.1.ffn.experts.mlp_experts.1.w1
- transformer.blocks.10.ffn.experts.mlp_experts.1.w1
# ffn.experts.mlp_experts.1.w2 layers
- transformer.blocks.25.ffn.experts.mlp_experts.1.w2
- transformer.blocks.23.ffn.experts.mlp_experts.1.w2
- transformer.blocks.27.ffn.experts.mlp_experts.1.w2
- transformer.blocks.29.ffn.experts.mlp_experts.1.w2
- transformer.blocks.31.ffn.experts.mlp_experts.1.w2
- transformer.blocks.4.ffn.experts.mlp_experts.1.w2
- transformer.blocks.32.ffn.experts.mlp_experts.1.w2
- transformer.blocks.30.ffn.experts.mlp_experts.1.w2
- transformer.blocks.21.ffn.experts.mlp_experts.1.w2
- transformer.blocks.33.ffn.experts.mlp_experts.1.w2
# ffn.experts.mlp_experts.10.v1 layers
- transformer.blocks.28.ffn.experts.mlp_experts.10.v1
- transformer.blocks.34.ffn.experts.mlp_experts.10.v1
- transformer.blocks.33.ffn.experts.mlp_experts.10.v1
- transformer.blocks.26.ffn.experts.mlp_experts.10.v1
- transformer.blocks.32.ffn.experts.mlp_experts.10.v1
- transformer.blocks.30.ffn.experts.mlp_experts.10.v1
- transformer.blocks.36.ffn.experts.mlp_experts.10.v1
- transformer.blocks.24.ffn.experts.mlp_experts.10.v1
- transformer.blocks.20.ffn.experts.mlp_experts.10.v1
- transformer.blocks.35.ffn.experts.mlp_experts.10.v1
# ffn.experts.mlp_experts.10.w1 layers
- transformer.blocks.24.ffn.experts.mlp_experts.10.w1
- transformer.blocks.33.ffn.experts.mlp_experts.10.w1
- transformer.blocks.8.ffn.experts.mlp_experts.10.w1
- transformer.blocks.7.ffn.experts.mlp_experts.10.w1
- transformer.blocks.34.ffn.experts.mlp_experts.10.w1
- transformer.blocks.28.ffn.experts.mlp_experts.10.w1
- transformer.blocks.30.ffn.experts.mlp_experts.10.w1
- transformer.blocks.1.ffn.experts.mlp_experts.10.w1
- transformer.blocks.3.ffn.experts.mlp_experts.10.w1
- transformer.blocks.5.ffn.experts.mlp_experts.10.w1
# ffn.experts.mlp_experts.10.w2 layers
- transformer.blocks.24.ffn.experts.mlp_experts.10.w2
- transformer.blocks.28.ffn.experts.mlp_experts.10.w2
- transformer.blocks.23.ffn.experts.mlp_experts.10.w2
- transformer.blocks.30.ffn.experts.mlp_experts.10.w2
- transformer.blocks.32.ffn.experts.mlp_experts.10.w2
- transformer.blocks.3.ffn.experts.mlp_experts.10.w2
- transformer.blocks.33.ffn.experts.mlp_experts.10.w2
- transformer.blocks.26.ffn.experts.mlp_experts.10.w2
- transformer.blocks.2.ffn.experts.mlp_experts.10.w2
- transformer.blocks.20.ffn.experts.mlp_experts.10.w2
# ffn.experts.mlp_experts.11.w1 layers
- transformer.blocks.6.ffn.experts.mlp_experts.11.w1
- transformer.blocks.8.ffn.experts.mlp_experts.11.w1
- transformer.blocks.9.ffn.experts.mlp_experts.11.w1
- transformer.blocks.0.ffn.experts.mlp_experts.11.w1
- transformer.blocks.10.ffn.experts.mlp_experts.11.w1
- transformer.blocks.28.ffn.experts.mlp_experts.11.w1
- transformer.blocks.3.ffn.experts.mlp_experts.11.w1
- transformer.blocks.5.ffn.experts.mlp_experts.11.w1
- transformer.blocks.33.ffn.experts.mlp_experts.11.w1
- transformer.blocks.13.ffn.experts.mlp_experts.11.w1
# ffn.experts.mlp_experts.11.w2 layers
- transformer.blocks.27.ffn.experts.mlp_experts.11.w2
- transformer.blocks.24.ffn.experts.mlp_experts.11.w2
- transformer.blocks.29.ffn.experts.mlp_experts.11.w2
- transformer.blocks.30.ffn.experts.mlp_experts.11.w2
- transformer.blocks.22.ffn.experts.mlp_experts.11.w2
- transformer.blocks.6.ffn.experts.mlp_experts.11.w2
- transformer.blocks.25.ffn.experts.mlp_experts.11.w2
- transformer.blocks.7.ffn.experts.mlp_experts.11.w2
- transformer.blocks.28.ffn.experts.mlp_experts.11.w2
- transformer.blocks.5.ffn.experts.mlp_experts.11.w2
# ffn.experts.mlp_experts.12.v1 layers
- transformer.blocks.30.ffn.experts.mlp_experts.12.v1
- transformer.blocks.21.ffn.experts.mlp_experts.12.v1
- transformer.blocks.27.ffn.experts.mlp_experts.12.v1
- transformer.blocks.28.ffn.experts.mlp_experts.12.v1
- transformer.blocks.29.ffn.experts.mlp_experts.12.v1
- transformer.blocks.8.ffn.experts.mlp_experts.12.v1
- transformer.blocks.10.ffn.experts.mlp_experts.12.v1
- transformer.blocks.23.ffn.experts.mlp_experts.12.v1
- transformer.blocks.6.ffn.experts.mlp_experts.12.v1
- transformer.blocks.20.ffn.experts.mlp_experts.12.v1
# ffn.experts.mlp_experts.12.w1 layers
- transformer.blocks.8.ffn.experts.mlp_experts.12.w1
- transformer.blocks.1.ffn.experts.mlp_experts.12.w1
- transformer.blocks.0.ffn.experts.mlp_experts.12.w1
- transformer.blocks.6.ffn.experts.mlp_experts.12.w1
- transformer.blocks.9.ffn.experts.mlp_experts.12.w1
- transformer.blocks.2.ffn.experts.mlp_experts.12.w1
- transformer.blocks.10.ffn.experts.mlp_experts.12.w1
- transformer.blocks.17.ffn.experts.mlp_experts.12.w1
- transformer.blocks.29.ffn.experts.mlp_experts.12.w1
- transformer.blocks.21.ffn.experts.mlp_experts.12.w1
# ffn.experts.mlp_experts.12.w2 layers
- transformer.blocks.6.ffn.experts.mlp_experts.12.w2
- transformer.blocks.25.ffn.experts.mlp_experts.12.w2
- transformer.blocks.27.ffn.experts.mlp_experts.12.w2
- transformer.blocks.8.ffn.experts.mlp_experts.12.w2
- transformer.blocks.31.ffn.experts.mlp_experts.12.w2
- transformer.blocks.21.ffn.experts.mlp_experts.12.w2
- transformer.blocks.2.ffn.experts.mlp_experts.12.w2
- transformer.blocks.29.ffn.experts.mlp_experts.12.w2
- transformer.blocks.32.ffn.experts.mlp_experts.12.w2
- transformer.blocks.30.ffn.experts.mlp_experts.12.w2
# ffn.experts.mlp_experts.13.v1 layers
- transformer.blocks.31.ffn.experts.mlp_experts.13.v1
- transformer.blocks.24.ffn.experts.mlp_experts.13.v1
- transformer.blocks.30.ffn.experts.mlp_experts.13.v1
- transformer.blocks.29.ffn.experts.mlp_experts.13.v1
- transformer.blocks.8.ffn.experts.mlp_experts.13.v1
- transformer.blocks.10.ffn.experts.mlp_experts.13.v1
- transformer.blocks.11.ffn.experts.mlp_experts.13.v1
- transformer.blocks.27.ffn.experts.mlp_experts.13.v1
- transformer.blocks.25.ffn.experts.mlp_experts.13.v1
- transformer.blocks.36.ffn.experts.mlp_experts.13.v1
# ffn.experts.mlp_experts.13.w1 layers
- transformer.blocks.4.ffn.experts.mlp_experts.13.w1
- transformer.blocks.10.ffn.experts.mlp_experts.13.w1
- transformer.blocks.6.ffn.experts.mlp_experts.13.w1
- transformer.blocks.0.ffn.experts.mlp_experts.13.w1
- transformer.blocks.3.ffn.experts.mlp_experts.13.w1
- transformer.blocks.24.ffn.experts.mlp_experts.13.w1
- transformer.blocks.8.ffn.experts.mlp_experts.13.w1
- transformer.blocks.1.ffn.experts.mlp_experts.13.w1
- transformer.blocks.30.ffn.experts.mlp_experts.13.w1
- transformer.blocks.11.ffn.experts.mlp_experts.13.w1
# ffn.experts.mlp_experts.13.w2 layers
- transformer.blocks.24.ffn.experts.mlp_experts.13.w2
- transformer.blocks.20.ffn.experts.mlp_experts.13.w2
- transformer.blocks.25.ffn.experts.mlp_experts.13.w2
- transformer.blocks.27.ffn.experts.mlp_experts.13.w2
- transformer.blocks.3.ffn.experts.mlp_experts.13.w2
- transformer.blocks.4.ffn.experts.mlp_experts.13.w2
- transformer.blocks.29.ffn.experts.mlp_experts.13.w2
- transformer.blocks.6.ffn.experts.mlp_experts.13.w2
- transformer.blocks.30.ffn.experts.mlp_experts.13.w2
- transformer.blocks.31.ffn.experts.mlp_experts.13.w2
# ffn.experts.mlp_experts.14.v1 layers
- transformer.blocks.28.ffn.experts.mlp_experts.14.v1
- transformer.blocks.26.ffn.experts.mlp_experts.14.v1
- transformer.blocks.29.ffn.experts.mlp_experts.14.v1
- transformer.blocks.35.ffn.experts.mlp_experts.14.v1
- transformer.blocks.24.ffn.experts.mlp_experts.14.v1
- transformer.blocks.8.ffn.experts.mlp_experts.14.v1
- transformer.blocks.32.ffn.experts.mlp_experts.14.v1
- transformer.blocks.15.ffn.experts.mlp_experts.14.v1
- transformer.blocks.11.ffn.experts.mlp_experts.14.v1
- transformer.blocks.22.ffn.experts.mlp_experts.14.v1
# ffn.experts.mlp_experts.14.w1 layers
- transformer.blocks.8.ffn.experts.mlp_experts.14.w1
- transformer.blocks.4.ffn.experts.mlp_experts.14.w1
- transformer.blocks.5.ffn.experts.mlp_experts.14.w1
- transformer.blocks.7.ffn.experts.mlp_experts.14.w1
- transformer.blocks.3.ffn.experts.mlp_experts.14.w1
- transformer.blocks.13.ffn.experts.mlp_experts.14.w1
- transformer.blocks.29.ffn.experts.mlp_experts.14.w1
- transformer.blocks.6.ffn.experts.mlp_experts.14.w1
- transformer.blocks.28.ffn.experts.mlp_experts.14.w1
- transformer.blocks.9.ffn.experts.mlp_experts.14.w1
# ffn.experts.mlp_experts.14.w2 layers
- transformer.blocks.26.ffn.experts.mlp_experts.14.w2
- transformer.blocks.24.ffn.experts.mlp_experts.14.w2
- transformer.blocks.29.ffn.experts.mlp_experts.14.w2
- transformer.blocks.28.ffn.experts.mlp_experts.14.w2
- transformer.blocks.31.ffn.experts.mlp_experts.14.w2
- transformer.blocks.5.ffn.experts.mlp_experts.14.w2
- transformer.blocks.4.ffn.experts.mlp_experts.14.w2
- transformer.blocks.32.ffn.experts.mlp_experts.14.w2
- transformer.blocks.6.ffn.experts.mlp_experts.14.w2
- transformer.blocks.22.ffn.experts.mlp_experts.14.w2
# ffn.experts.mlp_experts.15.v1 layers
- transformer.blocks.33.ffn.experts.mlp_experts.15.v1
- transformer.blocks.26.ffn.experts.mlp_experts.15.v1
- transformer.blocks.31.ffn.experts.mlp_experts.15.v1
- transformer.blocks.28.ffn.experts.mlp_experts.15.v1
- transformer.blocks.9.ffn.experts.mlp_experts.15.v1
- transformer.blocks.34.ffn.experts.mlp_experts.15.v1
- transformer.blocks.29.ffn.experts.mlp_experts.15.v1
- transformer.blocks.7.ffn.experts.mlp_experts.15.v1
- transformer.blocks.17.ffn.experts.mlp_experts.15.v1
- transformer.blocks.15.ffn.experts.mlp_experts.15.v1
# ffn.experts.mlp_experts.15.w1 layers
- transformer.blocks.6.ffn.experts.mlp_experts.15.w1
- transformer.blocks.9.ffn.experts.mlp_experts.15.w1
- transformer.blocks.0.ffn.experts.mlp_experts.15.w1
- transformer.blocks.7.ffn.experts.mlp_experts.15.w1
- transformer.blocks.14.ffn.experts.mlp_experts.15.w1
- transformer.blocks.33.ffn.experts.mlp_experts.15.w1
- transformer.blocks.34.ffn.experts.mlp_experts.15.w1
- transformer.blocks.10.ffn.experts.mlp_experts.15.w1
- transformer.blocks.5.ffn.experts.mlp_experts.15.w1
- transformer.blocks.29.ffn.experts.mlp_experts.15.w1
# ffn.experts.mlp_experts.15.w2 layers
- transformer.blocks.28.ffn.experts.mlp_experts.15.w2
- transformer.blocks.26.ffn.experts.mlp_experts.15.w2
- transformer.blocks.27.ffn.experts.mlp_experts.15.w2
- transformer.blocks.29.ffn.experts.mlp_experts.15.w2
- transformer.blocks.6.ffn.experts.mlp_experts.15.w2
- transformer.blocks.31.ffn.experts.mlp_experts.15.w2
- transformer.blocks.7.ffn.experts.mlp_experts.15.w2
- transformer.blocks.33.ffn.experts.mlp_experts.15.w2
- transformer.blocks.32.ffn.experts.mlp_experts.15.w2
- transformer.blocks.25.ffn.experts.mlp_experts.15.w2
# ffn.experts.mlp_experts.2.v1 layers
- transformer.blocks.31.ffn.experts.mlp_experts.2.v1
- transformer.blocks.27.ffn.experts.mlp_experts.2.v1
- transformer.blocks.28.ffn.experts.mlp_experts.2.v1
- transformer.blocks.30.ffn.experts.mlp_experts.2.v1
- transformer.blocks.23.ffn.experts.mlp_experts.2.v1
- transformer.blocks.32.ffn.experts.mlp_experts.2.v1
- transformer.blocks.35.ffn.experts.mlp_experts.2.v1
- transformer.blocks.7.ffn.experts.mlp_experts.2.v1
- transformer.blocks.21.ffn.experts.mlp_experts.2.v1
- transformer.blocks.15.ffn.experts.mlp_experts.2.v1
# ffn.experts.mlp_experts.2.w1 layers
- transformer.blocks.7.ffn.experts.mlp_experts.2.w1
- transformer.blocks.6.ffn.experts.mlp_experts.2.w1
- transformer.blocks.1.ffn.experts.mlp_experts.2.w1
- transformer.blocks.4.ffn.experts.mlp_experts.2.w1
- transformer.blocks.5.ffn.experts.mlp_experts.2.w1
- transformer.blocks.29.ffn.experts.mlp_experts.2.w1
- transformer.blocks.0.ffn.experts.mlp_experts.2.w1
- transformer.blocks.9.ffn.experts.mlp_experts.2.w1
- transformer.blocks.31.ffn.experts.mlp_experts.2.w1
- transformer.blocks.30.ffn.experts.mlp_experts.2.w1
# ffn.experts.mlp_experts.2.w2 layers
- transformer.blocks.26.ffn.experts.mlp_experts.2.w2
- transformer.blocks.27.ffn.experts.mlp_experts.2.w2
- transformer.blocks.33.ffn.experts.mlp_experts.2.w2
- transformer.blocks.5.ffn.experts.mlp_experts.2.w2
- transformer.blocks.23.ffn.experts.mlp_experts.2.w2
- transformer.blocks.32.ffn.experts.mlp_experts.2.w2
- transformer.blocks.28.ffn.experts.mlp_experts.2.w2
- transformer.blocks.4.ffn.experts.mlp_experts.2.w2
- transformer.blocks.29.ffn.experts.mlp_experts.2.w2
- transformer.blocks.30.ffn.experts.mlp_experts.2.w2
# ffn.experts.mlp_experts.3.v1 layers
- transformer.blocks.28.ffn.experts.mlp_experts.3.v1
- transformer.blocks.33.ffn.experts.mlp_experts.3.v1
- transformer.blocks.36.ffn.experts.mlp_experts.3.v1
- transformer.blocks.29.ffn.experts.mlp_experts.3.v1
- transformer.blocks.30.ffn.experts.mlp_experts.3.v1
- transformer.blocks.7.ffn.experts.mlp_experts.3.v1
- transformer.blocks.14.ffn.experts.mlp_experts.3.v1
- transformer.blocks.10.ffn.experts.mlp_experts.3.v1
- transformer.blocks.31.ffn.experts.mlp_experts.3.v1
- transformer.blocks.21.ffn.experts.mlp_experts.3.v1
# ffn.experts.mlp_experts.3.w1 layers
- transformer.blocks.7.ffn.experts.mlp_experts.3.w1
- transformer.blocks.0.ffn.experts.mlp_experts.3.w1
- transformer.blocks.10.ffn.experts.mlp_experts.3.w1
- transformer.blocks.9.ffn.experts.mlp_experts.3.w1
- transformer.blocks.29.ffn.experts.mlp_experts.3.w1
- transformer.blocks.5.ffn.experts.mlp_experts.3.w1
- transformer.blocks.30.ffn.experts.mlp_experts.3.w1
- transformer.blocks.4.ffn.experts.mlp_experts.3.w1
- transformer.blocks.33.ffn.experts.mlp_experts.3.w1
- transformer.blocks.1.ffn.experts.mlp_experts.3.w1
# ffn.experts.mlp_experts.3.w2 layers
- transformer.blocks.28.ffn.experts.mlp_experts.3.w2
- transformer.blocks.5.ffn.experts.mlp_experts.3.w2
- transformer.blocks.24.ffn.experts.mlp_experts.3.w2
- transformer.blocks.31.ffn.experts.mlp_experts.3.w2
- transformer.blocks.30.ffn.experts.mlp_experts.3.w2
- transformer.blocks.21.ffn.experts.mlp_experts.3.w2
- transformer.blocks.32.ffn.experts.mlp_experts.3.w2
- transformer.blocks.29.ffn.experts.mlp_experts.3.w2
- transformer.blocks.26.ffn.experts.mlp_experts.3.w2
- transformer.blocks.2.ffn.experts.mlp_experts.3.w2
# ffn.experts.mlp_experts.4.v1 layers
- transformer.blocks.34.ffn.experts.mlp_experts.4.v1
- transformer.blocks.31.ffn.experts.mlp_experts.4.v1
- transformer.blocks.26.ffn.experts.mlp_experts.4.v1
- transformer.blocks.24.ffn.experts.mlp_experts.4.v1
- transformer.blocks.14.ffn.experts.mlp_experts.4.v1
- transformer.blocks.32.ffn.experts.mlp_experts.4.v1
- transformer.blocks.7.ffn.experts.mlp_experts.4.v1
- transformer.blocks.6.ffn.experts.mlp_experts.4.v1
- transformer.blocks.20.ffn.experts.mlp_experts.4.v1
- transformer.blocks.9.ffn.experts.mlp_experts.4.v1
# ffn.experts.mlp_experts.4.w1 layers
- transformer.blocks.6.ffn.experts.mlp_experts.4.w1
- transformer.blocks.4.ffn.experts.mlp_experts.4.w1
- transformer.blocks.7.ffn.experts.mlp_experts.4.w1
- transformer.blocks.9.ffn.experts.mlp_experts.4.w1
- transformer.blocks.0.ffn.experts.mlp_experts.4.w1
- transformer.blocks.5.ffn.experts.mlp_experts.4.w1
- transformer.blocks.14.ffn.experts.mlp_experts.4.w1
- transformer.blocks.34.ffn.experts.mlp_experts.4.w1
- transformer.blocks.8.ffn.experts.mlp_experts.4.w1
- transformer.blocks.29.ffn.experts.mlp_experts.4.w1
# ffn.experts.mlp_experts.4.w2 layers
- transformer.blocks.25.ffn.experts.mlp_experts.4.w2
- transformer.blocks.24.ffn.experts.mlp_experts.4.w2
- transformer.blocks.26.ffn.experts.mlp_experts.4.w2
- transformer.blocks.5.ffn.experts.mlp_experts.4.w2
- transformer.blocks.6.ffn.experts.mlp_experts.4.w2
- transformer.blocks.32.ffn.experts.mlp_experts.4.w2
- transformer.blocks.4.ffn.experts.mlp_experts.4.w2
- transformer.blocks.36.ffn.experts.mlp_experts.4.w2
- transformer.blocks.29.ffn.experts.mlp_experts.4.w2
- transformer.blocks.27.ffn.experts.mlp_experts.4.w2
# ffn.experts.mlp_experts.5.v1 layers
- transformer.blocks.35.ffn.experts.mlp_experts.5.v1
- transformer.blocks.30.ffn.experts.mlp_experts.5.v1
- transformer.blocks.28.ffn.experts.mlp_experts.5.v1
- transformer.blocks.32.ffn.experts.mlp_experts.5.v1
- transformer.blocks.27.ffn.experts.mlp_experts.5.v1
- transformer.blocks.26.ffn.experts.mlp_experts.5.v1
- transformer.blocks.33.ffn.experts.mlp_experts.5.v1
- transformer.blocks.29.ffn.experts.mlp_experts.5.v1
- transformer.blocks.8.ffn.experts.mlp_experts.5.v1
- transformer.blocks.7.ffn.experts.mlp_experts.5.v1
# ffn.experts.mlp_experts.5.w1 layers
- transformer.blocks.0.ffn.experts.mlp_experts.5.w1
- transformer.blocks.6.ffn.experts.mlp_experts.5.w1
- transformer.blocks.7.ffn.experts.mlp_experts.5.w1
- transformer.blocks.9.ffn.experts.mlp_experts.5.w1
- transformer.blocks.8.ffn.experts.mlp_experts.5.w1
- transformer.blocks.12.ffn.experts.mlp_experts.5.w1
- transformer.blocks.3.ffn.experts.mlp_experts.5.w1
- transformer.blocks.5.ffn.experts.mlp_experts.5.w1
- transformer.blocks.4.ffn.experts.mlp_experts.5.w1
- transformer.blocks.33.ffn.experts.mlp_experts.5.w1
# ffn.experts.mlp_experts.5.w2 layers
- transformer.blocks.26.ffn.experts.mlp_experts.5.w2
- transformer.blocks.28.ffn.experts.mlp_experts.5.w2
- transformer.blocks.6.ffn.experts.mlp_experts.5.w2
- transformer.blocks.33.ffn.experts.mlp_experts.5.w2
- transformer.blocks.5.ffn.experts.mlp_experts.5.w2
- transformer.blocks.27.ffn.experts.mlp_experts.5.w2
- transformer.blocks.3.ffn.experts.mlp_experts.5.w2
- transformer.blocks.29.ffn.experts.mlp_experts.5.w2
- transformer.blocks.25.ffn.experts.mlp_experts.5.w2
- transformer.blocks.7.ffn.experts.mlp_experts.5.w2
# ffn.experts.mlp_experts.6.v1 layers
- transformer.blocks.34.ffn.experts.mlp_experts.6.v1
- transformer.blocks.31.ffn.experts.mlp_experts.6.v1
- transformer.blocks.30.ffn.experts.mlp_experts.6.v1
- transformer.blocks.26.ffn.experts.mlp_experts.6.v1
- transformer.blocks.35.ffn.experts.mlp_experts.6.v1
- transformer.blocks.20.ffn.experts.mlp_experts.6.v1
- transformer.blocks.15.ffn.experts.mlp_experts.6.v1
- transformer.blocks.29.ffn.experts.mlp_experts.6.v1
- transformer.blocks.10.ffn.experts.mlp_experts.6.v1
- transformer.blocks.24.ffn.experts.mlp_experts.6.v1
# ffn.experts.mlp_experts.6.w1 layers
- transformer.blocks.0.ffn.experts.mlp_experts.6.w1
- transformer.blocks.10.ffn.experts.mlp_experts.6.w1
- transformer.blocks.9.ffn.experts.mlp_experts.6.w1
- transformer.blocks.30.ffn.experts.mlp_experts.6.w1
- transformer.blocks.4.ffn.experts.mlp_experts.6.w1
- transformer.blocks.34.ffn.experts.mlp_experts.6.w1
- transformer.blocks.26.ffn.experts.mlp_experts.6.w1
- transformer.blocks.2.ffn.experts.mlp_experts.6.w1
- transformer.blocks.29.ffn.experts.mlp_experts.6.w1
- transformer.blocks.8.ffn.experts.mlp_experts.6.w1
# ffn.experts.mlp_experts.6.w2 layers
- transformer.blocks.24.ffn.experts.mlp_experts.6.w2
- transformer.blocks.26.ffn.experts.mlp_experts.6.w2
- transformer.blocks.32.ffn.experts.mlp_experts.6.w2
- transformer.blocks.30.ffn.experts.mlp_experts.6.w2
- transformer.blocks.25.ffn.experts.mlp_experts.6.w2
- transformer.blocks.31.ffn.experts.mlp_experts.6.w2
- transformer.blocks.20.ffn.experts.mlp_experts.6.w2
- transformer.blocks.4.ffn.experts.mlp_experts.6.w2
- transformer.blocks.2.ffn.experts.mlp_experts.6.w2
- transformer.blocks.9.ffn.experts.mlp_experts.6.w2
# ffn.experts.mlp_experts.7.v1 layers
- transformer.blocks.27.ffn.experts.mlp_experts.7.v1
- transformer.blocks.28.ffn.experts.mlp_experts.7.v1
- transformer.blocks.33.ffn.experts.mlp_experts.7.v1
- transformer.blocks.29.ffn.experts.mlp_experts.7.v1
- transformer.blocks.24.ffn.experts.mlp_experts.7.v1
- transformer.blocks.11.ffn.experts.mlp_experts.7.v1
- transformer.blocks.12.ffn.experts.mlp_experts.7.v1
- transformer.blocks.10.ffn.experts.mlp_experts.7.v1
- transformer.blocks.23.ffn.experts.mlp_experts.7.v1
- transformer.blocks.34.ffn.experts.mlp_experts.7.v1
# ffn.experts.mlp_experts.7.w1 layers
- transformer.blocks.12.ffn.experts.mlp_experts.7.w1
- transformer.blocks.0.ffn.experts.mlp_experts.7.w1
- transformer.blocks.5.ffn.experts.mlp_experts.7.w1
- transformer.blocks.29.ffn.experts.mlp_experts.7.w1
- transformer.blocks.10.ffn.experts.mlp_experts.7.w1
- transformer.blocks.4.ffn.experts.mlp_experts.7.w1
- transformer.blocks.3.ffn.experts.mlp_experts.7.w1
- transformer.blocks.8.ffn.experts.mlp_experts.7.w1
- transformer.blocks.34.ffn.experts.mlp_experts.7.w1
- transformer.blocks.33.ffn.experts.mlp_experts.7.w1
# ffn.experts.mlp_experts.7.w2 layers
- transformer.blocks.23.ffn.experts.mlp_experts.7.w2
- transformer.blocks.24.ffn.experts.mlp_experts.7.w2
- transformer.blocks.31.ffn.experts.mlp_experts.7.w2
- transformer.blocks.28.ffn.experts.mlp_experts.7.w2
- transformer.blocks.27.ffn.experts.mlp_experts.7.w2
- transformer.blocks.5.ffn.experts.mlp_experts.7.w2
- transformer.blocks.25.ffn.experts.mlp_experts.7.w2
- transformer.blocks.29.ffn.experts.mlp_experts.7.w2
- transformer.blocks.3.ffn.experts.mlp_experts.7.w2
- transformer.blocks.33.ffn.experts.mlp_experts.7.w2
# ffn.experts.mlp_experts.8.v1 layers
- transformer.blocks.30.ffn.experts.mlp_experts.8.v1
- transformer.blocks.27.ffn.experts.mlp_experts.8.v1
- transformer.blocks.20.ffn.experts.mlp_experts.8.v1
- transformer.blocks.32.ffn.experts.mlp_experts.8.v1
- transformer.blocks.34.ffn.experts.mlp_experts.8.v1
- transformer.blocks.33.ffn.experts.mlp_experts.8.v1
- transformer.blocks.9.ffn.experts.mlp_experts.8.v1
- transformer.blocks.7.ffn.experts.mlp_experts.8.v1
- transformer.blocks.6.ffn.experts.mlp_experts.8.v1
- transformer.blocks.24.ffn.experts.mlp_experts.8.v1
# ffn.experts.mlp_experts.8.w1 layers
- transformer.blocks.7.ffn.experts.mlp_experts.8.w1
- transformer.blocks.6.ffn.experts.mlp_experts.8.w1
- transformer.blocks.0.ffn.experts.mlp_experts.8.w1
- transformer.blocks.9.ffn.experts.mlp_experts.8.w1
- transformer.blocks.3.ffn.experts.mlp_experts.8.w1
- transformer.blocks.2.ffn.experts.mlp_experts.8.w1
- transformer.blocks.8.ffn.experts.mlp_experts.8.w1
- transformer.blocks.30.ffn.experts.mlp_experts.8.w1
- transformer.blocks.24.ffn.experts.mlp_experts.8.w1
- transformer.blocks.1.ffn.experts.mlp_experts.8.w1
# ffn.experts.mlp_experts.8.w2 layers
- transformer.blocks.32.ffn.experts.mlp_experts.8.w2
- transformer.blocks.24.ffn.experts.mlp_experts.8.w2
- transformer.blocks.27.ffn.experts.mlp_experts.8.w2
- transformer.blocks.30.ffn.experts.mlp_experts.8.w2
- transformer.blocks.31.ffn.experts.mlp_experts.8.w2
- transformer.blocks.28.ffn.experts.mlp_experts.8.w2
- transformer.blocks.2.ffn.experts.mlp_experts.8.w2
- transformer.blocks.3.ffn.experts.mlp_experts.8.w2
- transformer.blocks.23.ffn.experts.mlp_experts.8.w2
- transformer.blocks.29.ffn.experts.mlp_experts.8.w2
# ffn.experts.mlp_experts.9.v1 layers
- transformer.blocks.31.ffn.experts.mlp_experts.9.v1
- transformer.blocks.27.ffn.experts.mlp_experts.9.v1
- transformer.blocks.29.ffn.experts.mlp_experts.9.v1
- transformer.blocks.33.ffn.experts.mlp_experts.9.v1
- transformer.blocks.25.ffn.experts.mlp_experts.9.v1
- transformer.blocks.14.ffn.experts.mlp_experts.9.v1
- transformer.blocks.32.ffn.experts.mlp_experts.9.v1
- transformer.blocks.7.ffn.experts.mlp_experts.9.v1
- transformer.blocks.9.ffn.experts.mlp_experts.9.v1
- transformer.blocks.34.ffn.experts.mlp_experts.9.v1
# ffn.experts.mlp_experts.9.w1 layers
- transformer.blocks.7.ffn.experts.mlp_experts.9.w1
- transformer.blocks.1.ffn.experts.mlp_experts.9.w1
- transformer.blocks.9.ffn.experts.mlp_experts.9.w1
- transformer.blocks.2.ffn.experts.mlp_experts.9.w1
- transformer.blocks.27.ffn.experts.mlp_experts.9.w1
- transformer.blocks.12.ffn.experts.mlp_experts.9.w1
- transformer.blocks.4.ffn.experts.mlp_experts.9.w1
- transformer.blocks.6.ffn.experts.mlp_experts.9.w1
- transformer.blocks.19.ffn.experts.mlp_experts.9.w1
- transformer.blocks.8.ffn.experts.mlp_experts.9.w1
# ffn.experts.mlp_experts.9.w2 layers
- transformer.blocks.26.ffn.experts.mlp_experts.9.w2
- transformer.blocks.25.ffn.experts.mlp_experts.9.w2
- transformer.blocks.28.ffn.experts.mlp_experts.9.w2
- transformer.blocks.27.ffn.experts.mlp_experts.9.w2
- transformer.blocks.31.ffn.experts.mlp_experts.9.w2
- transformer.blocks.29.ffn.experts.mlp_experts.9.w2
- transformer.blocks.7.ffn.experts.mlp_experts.9.w2
- transformer.blocks.34.ffn.experts.mlp_experts.9.w2
- transformer.blocks.2.ffn.experts.mlp_experts.9.w2
- transformer.blocks.33.ffn.experts.mlp_experts.9.w2
# ffn.router.layer layers
- transformer.blocks.2.ffn.router.layer
- transformer.blocks.3.ffn.router.layer
- transformer.blocks.4.ffn.router.layer
- transformer.blocks.5.ffn.router.layer
- transformer.blocks.6.ffn.router.layer
- transformer.blocks.7.ffn.router.layer
- transformer.blocks.8.ffn.router.layer
- transformer.blocks.9.ffn.router.layer
- transformer.blocks.10.ffn.router.layer
- transformer.blocks.11.ffn.router.layer
# norm_attn_norm.attn.Wqkv layers
- transformer.blocks.16.norm_attn_norm.attn.Wqkv
- transformer.blocks.15.norm_attn_norm.attn.Wqkv
- transformer.blocks.11.norm_attn_norm.attn.Wqkv
- transformer.blocks.14.norm_attn_norm.attn.Wqkv
- transformer.blocks.12.norm_attn_norm.attn.Wqkv
- transformer.blocks.20.norm_attn_norm.attn.Wqkv
- transformer.blocks.10.norm_attn_norm.attn.Wqkv
- transformer.blocks.9.norm_attn_norm.attn.Wqkv
- transformer.blocks.19.norm_attn_norm.attn.Wqkv
- transformer.blocks.18.norm_attn_norm.attn.Wqkv
# norm_attn_norm.attn.out_proj layers
- transformer.blocks.1.norm_attn_norm.attn.out_proj
- transformer.blocks.18.norm_attn_norm.attn.out_proj
- transformer.blocks.2.norm_attn_norm.attn.out_proj
- transformer.blocks.16.norm_attn_norm.attn.out_proj
- transformer.blocks.0.norm_attn_norm.attn.out_proj
- transformer.blocks.39.norm_attn_norm.attn.out_proj
- transformer.blocks.23.norm_attn_norm.attn.out_proj
- transformer.blocks.8.norm_attn_norm.attn.out_proj
- transformer.blocks.24.norm_attn_norm.attn.out_proj
- transformer.blocks.19.norm_attn_norm.attn.out_proj
# norm_attn_norm.norm_1 layers
- transformer.blocks.0.norm_attn_norm.norm_1
- transformer.blocks.1.norm_attn_norm.norm_1
- transformer.blocks.2.norm_attn_norm.norm_1
- transformer.blocks.3.norm_attn_norm.norm_1
- transformer.blocks.4.norm_attn_norm.norm_1
- transformer.blocks.5.norm_attn_norm.norm_1
- transformer.blocks.6.norm_attn_norm.norm_1
- transformer.blocks.7.norm_attn_norm.norm_1
- transformer.blocks.8.norm_attn_norm.norm_1
- transformer.blocks.9.norm_attn_norm.norm_1
# norm_attn_norm.norm_2 layers
- transformer.blocks.0.norm_attn_norm.norm_2
- transformer.blocks.1.norm_attn_norm.norm_2
- transformer.blocks.2.norm_attn_norm.norm_2
- transformer.blocks.3.norm_attn_norm.norm_2
- transformer.blocks.4.norm_attn_norm.norm_2
- transformer.blocks.5.norm_attn_norm.norm_2
- transformer.blocks.6.norm_attn_norm.norm_2
- transformer.blocks.7.norm_attn_norm.norm_2
- transformer.blocks.8.norm_attn_norm.norm_2
- transformer.blocks.9.norm_attn_norm.norm_2
# transformer.norm_f layers
# transformer.wte layers
# ffn.experts.mlp_experts.11.v1 layers
- transformer.blocks.29.ffn.experts.mlp_experts.11.v1
- transformer.blocks.27.ffn.experts.mlp_experts.11.v1
- transformer.blocks.30.ffn.experts.mlp_experts.11.v1
- transformer.blocks.28.ffn.experts.mlp_experts.11.v1
- transformer.blocks.22.ffn.experts.mlp_experts.11.v1
- transformer.blocks.7.ffn.experts.mlp_experts.11.v1
- transformer.blocks.24.ffn.experts.mlp_experts.11.v1
- transformer.blocks.8.ffn.experts.mlp_experts.11.v1
- transformer.blocks.6.ffn.experts.mlp_experts.11.v1
- transformer.blocks.12.ffn.experts.mlp_experts.11.v1



dataset_prepared_path: dbrx2
val_set_size: 0.01
output_dir: ./out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

wandb_project: dolphin-2.9-Dbrx
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
# resume_from_checkpoint: /workspace/axolotl/dbrx-checkpoint
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 4
save_total_limit: 2
save_steps:
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|endoftext|>"
  eos_token: "<|im_end|>"
  pad_token: "<|pad|>"
  unk_token: "<|endoftext|>"
tokens:
  - "<|im_start|>"
  - "<|im_end|>"

out

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4336

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.4009	0.0	1	0.4328
0.413	0.25	587	0.4408
0.3626	0.5	1174	0.4368
0.3896	0.75	1761	0.4336

Framework versions

Transformers 4.40.0.dev0
Pytorch 2.2.2+cu121
Datasets 2.15.0
Tokenizers 0.15.0

Как запустить

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

GPU в ailist

vLLM

Можно запустить

Подбираем GPU…

Класс архитектуры: DbrxForCausalLM
Ревизия весов: afd0107

Характеристики

Ссылки

dolphin-2.9.1-dbrx

Бенчмарки

Тесты пользователейпока нет

Добавьте модель в бенчмарк

Опишите свои задачи

Запустите и опубликуйте

Публичные оценки

Что умеет модель

Сценарии применения

Ограничения

Для каких профессий подходит15

Также подходит для

Карточка модели

Dolphin 2.9.1 DBRX 🐬

Evals

Training

out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Как запустить