mrfakename/mistral-small-3.1-24b-instruct-2503-hf
Hugging Face
VISIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:Mar 17, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

mrfakename/mistral-small-3.1-24b-instruct-2503-hf is a 24 billion parameter instruction-tuned language model, converted to the Hugging Face format by mrfakename. This model is based on the Mistral Small 3.1 Instruct 24B architecture. It is specifically designed for text-based tasks, as its vision capabilities were not retained during the conversion process. Its primary utility lies in instruction-following for natural language processing applications.

Loading preview...

Overview

This model, mrfakename/mistral-small-3.1-24b-instruct-2503-hf, is a 24 billion parameter instruction-tuned language model. It is a Hugging Face format conversion of the original Mistral Small 3.1 Instruct 24B model. The conversion process specifically focused on the text component, meaning that any vision capabilities present in the original model were not carried over.

Key Characteristics

  • Model Size: 24 billion parameters.
  • Base Model: Derived from Mistral Small 3.1 Instruct 24B.
  • Format: Converted to Hugging Face format for broader compatibility.
  • Functionality: Optimized for instruction-following in text-based tasks.
  • Limitation: Does not support vision inputs; it functions exclusively as a text model.

Use Cases

This model is suitable for developers requiring a powerful, instruction-tuned language model for various NLP applications, particularly those involving:

  • Generating human-like text based on instructions.
  • Answering questions.
  • Summarization.
  • Text completion.

It is important to note that for tasks requiring multimodal (vision) capabilities, this specific model version is not appropriate.

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