megastudyedu/M-SOLAR-10.7B-v1.3

Hugging Face
TEXT GENERATIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:10.7BQuant:FP8Context Size:4kLicense:cc-by-nc-nd-4.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Warm

M-SOLAR-10.7B-v1.3 is a 10.7 billion parameter language model developed by megastudyedu, Prediction, and MICE. This model is an enhanced version of megastudy/M-SOLAR-10.7B-v1.1-beta, further fine-tuned with additional in-house datasets and increased random shuffle generation data. It is designed for general language understanding and generation tasks, building upon its predecessor's capabilities.

Loading preview...

Overview

M-SOLAR-10.7B-v1.3 is a 10.7 billion parameter language model developed collaboratively by megastudyedu, Prediction, and MICE. It is an iteration built upon the foundation of the megastudy/M-SOLAR-10.7B-v1.1-beta model.

Key Enhancements

  • Expanded Dataset: The model has been further trained by incorporating additional, processed in-house datasets beyond those used for its base model.
  • Data Augmentation: The quantity of data generated through random shuffling has been increased, contributing to a more robust training regimen.

Intended Use

This model is suitable for a variety of natural language processing tasks, leveraging its 10.7 billion parameters and refined training data to offer improved performance over its base version. Its enhancements suggest a focus on general-purpose language understanding and generation, making it a versatile tool for developers.

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