Calme 7B Instruct V0.9

🚀 MaziyarPanahi/Calme-7B-Instruct-v0.9

Calme-7B-Instruct-v0.9 is a state - of - the - art language model. It has 7 billion parameters and is fine - tuned on high - quality datasets based on Mistral - 7B. This model can generate clear, calm, and coherent text.

✨ Features

• High - Quality Text Generation: Calme-7B models are excellent at generating text that is clear, calm, and coherent.
• Quantized Models: Available in GGUF format (2/3/4/5/6/8 bits), making it accessible on commodity hardware.

📦 Installation

There is no specific installation command provided in the original text. However, the usage code implies that the transformers library needs to be installed. You can install it via the following command:

pip install transformers

💻 Usage Examples

Basic Usage

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

pipe = pipeline("text-generation", model="MaziyarPanahi/Calme-7B-Instruct-v0.9")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Calme-7B-Instruct-v0.9")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Calme-7B-Instruct-v0.9")

Advanced Usage

The advanced usage here is related to the quantized models.

# Although no specific code for using quantized models is provided, 
# you can load the quantized model in a similar way as the normal model
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Calme-7B-Instruct-v0.9-GGUF")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Calme-7B-Instruct-v0.9-GGUF")

📚 Documentation

Quantized Models

I love how GGUF democratizes the use of Large Language Models (LLMs) on commodity hardware, more specifically, personal computers without any accelerated hardware. Because of this, I am committed to converting and quantizing any models I fine - tune to make them accessible to everyone!

• GGUF (2/3/4/5/6/8 bits): MaziyarPanahi/Calme-7B-Instruct-v0.9-GGUF

Multilingual Examples

<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]

<s> [INST] Mark is faster than Mary, Mary is faster than Joe. Is Joe faster than Mark? Let's think step by step [/INST]

<s> [INST] explain step by step 25-4*2+3=? [/INST]

Multilingual:

<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]

<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]