metadata

license: apache-2.0
tags:
  - generated_from_trainer
  - mistral
  - 7b
  - calme
model-index:
  - name: Calme-7B-Instruct-v0.1.1
    results: []
datasets:
  - ise-uiuc/Magicoder-Evol-Instruct-110K
model_name: Calme-7B-Instruct-v0.1.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi

MaziyarPanahi/Calme-7B-Instruct-v0.1

Model Description

Calme-7B is a state-of-the-art language model with 7 billion parameters, fine-tuned over high-quality datasets on top of Mistral-7B. The Calme-7B models excel in generating text that resonates with 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-7B-Instruct-v0.1.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Calme-7B-Instruct-v0.1.1")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Calme-7B-Instruct-v0.1.1")

Quantized Models

coming soon

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

<s> [INST] There are three killers in a room. Someone enters the room and kills one of them. Nobody leaves the room. How many killers are left in the room? Explain your reasoning step by step. [/INST]

Show me the response

Multilingual:

Show me the response