MNCLLM/Mistral-7B-orca-platy-over1k

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kLicense:apache-2.0Architecture:Transformer Open Weights Cold

MNCLLM/Mistral-7B-orca-platy-over1k is a language model developed by Minds And Company, built upon the Mistral-7B-v0.1 backbone. This model is fine-tuned using Orca-style and Alpaca-style datasets, leveraging the Llama Prompt Template for instruction following. It is designed for general-purpose conversational AI and instruction-based tasks, offering enhanced response quality through its specialized training data.

Loading preview...

Model Overview

MNCLLM/Mistral-7B-orca-platy-over1k is a language model developed by Minds And Company, utilizing the robust Mistral-7B-v0.1 as its foundational backbone. This model is integrated with the HuggingFace Transformers library, ensuring broad compatibility and ease of use within the AI ecosystem.

Key Capabilities

  • Instruction Following: The model is fine-tuned with a combination of Orca-style and Alpaca-style datasets, which are known for improving instruction-following capabilities and conversational coherence.
  • Prompt Template Adherence: It specifically uses the Llama Prompt Template, guiding its responses to be structured and relevant to user queries.

Good For

  • General Conversational AI: Its training on diverse instruction datasets makes it suitable for various dialogue-based applications.
  • Instruction-Based Tasks: Excels in scenarios requiring the model to follow specific instructions or complete defined tasks based on prompts.

Training Details

The model's enhanced performance stems from its fine-tuning on two distinct types of datasets:

  • Orca-style dataset: Contributes to advanced reasoning and complex instruction understanding.
  • Alpaca-style dataset: Focuses on generating helpful and safe responses across a wide range of topics.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p