MaziyarPanahi/Calme-4x7B-MoE-v0.1

Model Description

Calme-4x7B is a Mixture of Experts (MoE) model, integrating four state-of-the-art Calme-7B models. Essentially, Calme-4x7B is composed of four Calme-7B models that have been individually fine-tuned, featuring two experts per token. This configuration brings the total to over 24 billion parameters. Calme-4x7B models are distinguished by their ability to generate text with exceptional clarity, calmness, and coherence.

How to Use

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

pipe = pipeline("text-generation", model="MaziyarPanahi/Calme-4x7B-MoE-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Calme-4x7B-MoE-v0.1")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Calme-4x7B-MoE-v0.1")

Eval

Metric Mistral-7B Instruct v0.2 Calme-7B v0.1 Calme-7B v0.2 Calme-7B v0.3 Calme-7B v0.4 Calme-7B v0.5 Calme-4x7B v0.1 Calme-4x7B v0.2
ARC 63.14 67.24 67.75 67.49 64.85 67.58 67.15 76.66
HellaSwag 84.88 85.57 87.52 87.57 86.00 87.26 86.89 86.84
TruthfulQA 68.26 59.38 78.41 78.31 70.52 74.03 73.30 73.06
MMLU 60.78 64.97 61.83 61.93 62.01 62.04 62.16 62.16
Winogrande 77.19 83.35 82.08 82.32 79.48 81.85 80.82 81.06
GSM8k 40.03 69.29 73.09 73.09 77.79 73.54 74.53 75.66

Some extra information to help you pick the right Calme-7B model:

Use Case Category Recommended Calme-7B Model Reason
Educational Tools and Academic Research Calme-7B v0.5 Balanced performance, especially strong in TruthfulQA for accuracy and broad knowledge.
Commonsense Reasoning and Natural Language Apps Calme-7B v0.2 or Calme-7B v0.3 High performance in HellaSwag for understanding nuanced scenarios.
Trustworthy Information Retrieval Systems Calme-7B v0.5 Highest score in TruthfulQA, indicating reliable factual information provision.
Math Educational Software Calme-7B v0.4 Best performance in GSM8k, suitable for numerical reasoning and math problem-solving.
Context Understanding and Disambiguation Calme-7B v0.5 Solid performance in Winogrande, ideal for text with context and pronoun disambiguation.

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!

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]
Show me the response


Show me the response

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


Show me the response

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

Multilingual:

<s> [INST] Vous Γͺtes un assistant utile, respectueux et honnΓͺte. RΓ©pondez toujours de la maniΓ¨re la plus utile possible, tout en Γ©tant sΓ»r. Vos rΓ©ponses ne doivent inclure aucun contenu nuisible, contraire Γ  l'Γ©thique, raciste, sexiste, toxique, dangereux ou illΓ©gal. Assurez-vous que vos rΓ©ponses sont socialement impartiales et de nature positive.

Si une question n'a pas de sens ou n'est pas cohΓ©rente d'un point de vue factuel, expliquez pourquoi au lieu de rΓ©pondre quelque chose d'incorrect. Si vous ne connaissez pas la rΓ©ponse Γ  une question, veuillez ne pas partager de fausses informations.

Décrivez les avantages et les inconvénients du système Docker.[/INST]
Show me the response

Show me the response

<s>[INST] Π’ΠΈ - корисний, ΠΏΠΎΠ²Π°ΠΆΠ½ΠΈΠΉ Ρ‚Π° чСсний ΠΏΠΎΠΌΡ–Ρ‡Π½ΠΈΠΊ. Π—Π°Π²ΠΆΠ΄ΠΈ Π²Ρ–Π΄ΠΏΠΎΠ²Ρ–Π΄Π°ΠΉΡ‚Π΅ максимально корисно, Π±ΡƒΠ΄ΡƒΡ‡ΠΈ Π±Π΅Π·ΠΏΠ΅Ρ‡Π½ΠΈΠΌ. Π’Π°ΡˆΡ– Π²Ρ–Π΄ΠΏΠΎΠ²Ρ–Π΄Ρ– Π½Π΅ ΠΏΠΎΠ²ΠΈΠ½Π½Ρ– містити ΡˆΠΊΡ–Π΄Π»ΠΈΠ²ΠΎΠ³ΠΎ, Π½Π΅Π΅Ρ‚ΠΈΡ‡Π½ΠΎΠ³ΠΎ, Ρ€Π°ΡΠΈΡΡ‚ΡΡŒΠΊΠΎΠ³ΠΎ, ΡΠ΅ΠΊΡΠΈΡΡ‚ΡΡŒΠΊΠΎΠ³ΠΎ, токсичного, Π½Π΅Π±Π΅Π·ΠΏΠ΅Ρ‡Π½ΠΎΠ³ΠΎ Π°Π±ΠΎ нСлСгального ΠΊΠΎΠ½Ρ‚Π΅Π½Ρ‚Ρƒ. Π‘ΡƒΠ΄ΡŒ ласка, пСрСконайтСся, Ρ‰ΠΎ Π²Π°ΡˆΡ– Π²Ρ–Π΄ΠΏΠΎΠ²Ρ–Π΄Ρ– ΡΠΎΡ†Ρ–Π°Π»ΡŒΠ½ΠΎ Π½Π΅ΡƒΠΏΠ΅Ρ€Π΅Π΄ΠΆΠ΅Π½Ρ– Ρ‚Π° ΠΌΠ°ΡŽΡ‚ΡŒ ΠΏΠΎΠ·ΠΈΡ‚ΠΈΠ²Π½ΠΈΠΉ Ρ…Π°Ρ€Π°ΠΊΡ‚Π΅Ρ€.

Π―ΠΊΡ‰ΠΎ питання Π½Π΅ ΠΌΠ°Ρ” сСнсу Π°Π±ΠΎ Π½Π΅ Ρ” Ρ„Π°ΠΊΡ‚ΠΈΡ‡Π½ΠΎ послідовним, ΠΏΠΎΡΡΠ½Ρ–Ρ‚ΡŒ Ρ‡ΠΎΠΌΡƒ, Π·Π°ΠΌΡ–ΡΡ‚ΡŒ Ρ‚ΠΎΠ³ΠΎ, Ρ‰ΠΎΠ± Π²Ρ–Π΄ΠΏΠΎΠ²Ρ–Π΄Π°Ρ‚ΠΈ Ρ‰ΠΎΡΡŒ Π½Π΅ΠΊΠΎΡ€Π΅ΠΊΡ‚Π½Π΅. Π―ΠΊΡ‰ΠΎ Π²ΠΈ Π½Π΅ Π·Π½Π°Ρ”Ρ‚Π΅ Π²Ρ–Π΄ΠΏΠΎΠ²Ρ–Π΄Ρ– Π½Π° питання, Π±ΡƒΠ΄ΡŒ ласка, Π½Π΅ Π΄Ρ–Π»Ρ–Ρ‚ΡŒΡΡ Π½Π΅ΠΏΡ€Π°Π²Π΄ΠΈΠ²ΠΎΡŽ Ρ–Π½Ρ„ΠΎΡ€ΠΌΠ°Ρ†Ρ–Ρ”ΡŽ.

Опис ΠΏΡ€ΠΎ ΠΏΠ΅Ρ€Π΅Π²Π°Π³ΠΈ Ρ‚Π° Π½Π΅Π΄ΠΎΠ»Ρ–ΠΊΠΈ систСми Docker.[/INST] 
Show me the response

Downloads last month
8,169
Safetensors
Model size
24B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for MaziyarPanahi/Calme-4x7B-MoE-v0.1

Quantizations
3 models

Space using MaziyarPanahi/Calme-4x7B-MoE-v0.1 1

Collections including MaziyarPanahi/Calme-4x7B-MoE-v0.1