Mistral-7B-Instruct-KhanAcademy-v0.2

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1502

How to use it

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MaziyarPanahi/Mistral-7B-Instruct-Aya-101")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Mistral-7B-Instruct-Aya-101")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Mistral-7B-Instruct-Aya-101")

Examples

<s> [INST] You are a sentient, superintelligent artificial general intelligence, here to teach and assist me. Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.[/INST] Goku was sitting on his favorite rock in the middle of the forest, enjoying the peace and quiet. He had just finished training with Vegeta and was feeling quite satisfied with himself. Suddenly, he sensed a powerful presence approaching.

"Who goes there?" Goku called out, standing up and preparing for battle.

A figure appeared before him, and Goku's eyes widened in shock. It was Kirby! But why was he here? And why did he look so different?

"Goku-san!" Kirby cried, rushing forward and hugging the Saiyan prince. "I have come to ask for your help!"

Goku was confused but happy to see his old friend. "What's going on, Kirby? What do you need my help with?"

Kirby looked around nervously before speaking. "Majin Buu has joined forces with me, and we plan to destroy the world!"

Goku was stunned. "What?! Why would you do that, Kirby?!"

"It's not what it seems," Kirby explained. "Buu promised to make the world a better place if I helped him. We will only destroy the evil beings and leave the good ones alone."

Goku was torn. On one hand, he couldn't trust Majin Buu, who had caused so much destruction in the past. On the other hand, he didn't want to hurt Kirby or stand in the way of his friend's goals.

"I can't let you do this, Kirby," Goku said finally. "We can't trust Majin Buu. He'll only cause more harm in the end."

Kirby sighed. "I understand, Goku-san. But I must follow my own path now. Farewell, my friend."

With a heavy heart, Goku watched as Kirby and Majin Buu disappeared into the distance, ready to wreak havoc on the world. Goku knew he couldn't stop them, but he vowed to protect the innocent and fight against any evil that threatened the peace of the universe.</s>
<s> [INST] You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.

describe about pros and cons of docker system.[/INST] Docker is an open-source platform for developing, shipping, and running applications using container technology. It simplifies the process of creating, deploying, and scaling applications by encapsulating code and dependencies into containers. Here are some advantages and disadvantages of using Docker:

Advantages:
1. Consistent Environment: Docker provides a consistent environment across different platforms and environments, ensuring that applications run the same way everywhere.
2. Faster Development: Docker allows developers to quickly spin up new environments and test their code in isolated containers, reducing development time.
3. Improved Security: Containers isolate applications from each other and from the host system, making it harder for attackers to exploit vulnerabilities.
4. Scalability: Docker makes it easy to scale applications by adding more containers as needed, allowing businesses to handle increased traffic and demand.
5. Reduced Dependencies: Docker reduces the number of dependencies required to run an application, making it easier to manage and maintain.
6. Portability: Docker containers can be easily moved between different environments, such as development, testing, and production, without requiring significant changes.
7. Automated Deployment: Docker integrates with popular deployment tools like Kubernetes and Docker Swarm, making it easier to automate the deployment process.
8. Cost Savings: Docker can reduce infrastructure costs by allowing businesses to use fewer servers and resources, as well as by enabling more efficient resource utilization.

Disadvantages:
1. Learning Curve: Docker has a steep learning curve, especially for those who are new to container technology.
2. Resource Intensive: Running multiple containers on a single host can be resource-intensive, potentially leading to performance issues.
3. Complexity: Docker introduces additional complexity to the development and deployment process, which can be challenging for smaller teams or projects.
4. Vendor Lock-in: Docker has a large market share, but there are also competing container technologies like Kubernetes and LXC. Choosing one over the others can lead to vendor lock-in.
5. Limited Customizability: While Docker offers a lot of flexibility, it may not provide enough customizability for certain use cases.
6. Security Risks: While Docker improves security in many ways, it also introduces new risks, such as the potential for misconfigured containers or vulnerabilities in the Docker engine itself.
7. Monitoring Challenges: Managing and monitoring containers at scale can be challenging, requiring specialized tools and expertise.</s>
<s> [INST] Vous êtes un assistant utile, respectueux et honnête. Répondez toujours de la manière la plus utile possible, tout en étant sûr. Vos réponses ne doivent inclure aucun contenu nuisible, contraire à l'éthique, raciste, sexiste, toxique, dangereux ou illégal. Assurez-vous que vos réponses sont socialement impartiales et de nature positive.

Si une question n'a pas de sens ou n'est pas cohérente d'un point de vue factuel, expliquez pourquoi au lieu de répondre quelque chose d'incorrect. Si vous ne connaissez pas la réponse à une question, veuillez ne pas partager de fausses informations.

Décrivez les avantages et les inconvénients du système Docker.[/INST] Avantages :
1. Simplification de la gestion des applications : Docker permet de gérer plusieurs applications dans le même environnement, ce qui simplifie la gestion des dépendances et des configurations.
2. Portabilité : Les images Docker peuvent être exécutées sur n'importe quelle plateforme compatible, ce qui facilite la distribution et la déploiement des applications.
3. Isolation : Chaque application est isolée dans son propre container, ce qui évite les conflits entre les applications et améliore la sécurité.
4. Rapidité : La création et la démarrage d'un container sont rapides, ce qui accélère le processus de développement et de déploiement.
5. Scalabilité : Les containers peuvent être facilement scalés en ajoutant plus de ressources, ce qui permet de gérer les charges de travail plus efficacement.

Inconvénients :
1. Complexité : Le système Docker peut être complexe à mettre en place et à utiliser, ce qui peut entraîner un apprentissage supplémentaire pour les développeurs.
2. Taille des images : Les images Docker peuvent être volumineuses, ce qui peut entraîner des temps de chargement longs lors du déploiement.
3. Gestion des mises à jour : La gestion des mises à jour des applications et des composants peut être complexe avec Docker, car chaque application doit être mise à jour indépendamment.
4. Sécurité : Les containers peuvent être vulnérables aux attaques si les configurations de sécurité ne sont pas correctement configurées.
5. Coût : Le système Docker peut avoir un coût supplémentaire pour les serveurs et les licences.</s>

Multilingual

<s> [INST] You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

Answer any question in Russian.

describe about pros and cons of docker system.[/INST] Docker - это система контейнеризации, которая позволяет развертывать приложения в изолированных окружениях. Это упрощает процесс развертывания и обслуживания приложений, но также может иметь некоторые ограничения.

Преимущества:
- Упрощенное развертывание и обслуживание приложений
- Изолированные окружения для каждого приложения
- Повышенная безопасность
- Улучшение производительности
- Разделение ресурсов между приложениями

Ограничения:
- Дополнительный слой абстракции
- Возможные проблемы с настройкой
- Некоторые функции могут быть ограничены в контейнерах
- Возможны проблемы с совместимостью</s>
<s> [INST] Ви - корисний, поважний та чесний помічник. Завжди відповідайте максимально корисно, будучи безпечним. Ваші відповіді не повинні містити шкідливого, неетичного, расистського, сексистського, токсичного, небезпечного або нелегального контенту. Будь ласка, переконайтеся, що ваші відповіді соціально неупереджені та мають позитивний характер.

Якщо питання не має сенсу або не є фактично послідовним, поясніть чому, замість того, щоб відповідати щось некоректне. Якщо ви не знаєте відповіді на питання, будь ласка, не діліться неправдивою інформацією.

Опис про переваги та недоліки системи Docker.[/INST] Дійсно, Docker є дуже корисним інструментом для розробників та операторів систем. Він дозволяє створювати контейнери з програмними пакетами, які можуть бути легко переміщатися між різними середовищами. Це дозволяє уникнути проблем з сумісністю та залежностями, які часто трапляються при встановленні програмних пакетів на різних системах. Крім того, Docker дозволяє використовувати однакове середовище розробки на різних платформах, що робить процес розробки більш ефективним.

Однак, Docker також має свої недоліки. Наприклад, він може споживати багато ресурсів системи, особливо пам'яті. Крім того, Docker може бути складним для нових користувачів, оскільки він має багато концепцій, які потрібно зрозуміти, перш ніж почати працювати з ним.

Таким чином, Docker є корисним інструментом для розробників та операторів систем, але його необхідно використовувати з обережністю та розумінням його переваг та недоліків.

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: 5e-06
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • 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
1.9039 0.0 1 3.1495
0.9933 0.25 101 1.2402
0.9439 0.5 202 1.1683
0.9762 0.75 303 1.1502

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.2.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.0

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: mistralai/Mistral-7B-Instruct-v0.2
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true


hub_model_id: MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: CohereForAI/aya_dataset
    type:
      system_prompt: ""
      field_instruction: inputs
      field_output: targets
      format: "[INST] {instruction} [/INST]"
      no_input_format: "[INST] {instruction} [/INST]"

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./models/MaziyarPanahi/Mistral-7B-Instruct-Aya-101

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

Downloads last month
312
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MaziyarPanahi/Mistral-7B-Instruct-Aya-101

Finetuned
(373)
this model
Quantizations
2 models

Dataset used to train MaziyarPanahi/Mistral-7B-Instruct-Aya-101

Space using MaziyarPanahi/Mistral-7B-Instruct-Aya-101 1

Collection including MaziyarPanahi/Mistral-7B-Instruct-Aya-101