Home › Language Models › STILL-3-Tool-32B

STILL-3-Tool-32B - AI Language Models Tool

Overview

STILL-3-Tool-32B is a 32.8B-parameter text-generation model that integrates Python code to enhance reasoning via tool manipulation. Open-sourced on Hugging Face, it achieved 81.70% accuracy on AIME 2024, matching o3-mini and outperforming o1 and DeepSeek-R1.

Key Features

  • 32.8B-parameter text-generation model
  • Integrates Python code to manipulate tools during reasoning
  • Designed to improve reasoning via integrated tool use
  • 81.70% accuracy on AIME 2024 benchmark
  • Open-sourced and hosted on Hugging Face

Ideal Use Cases

  • Research into tool-augmented reasoning systems
  • Solving math and logic benchmark problems
  • Prototyping applications requiring Python tool integration
  • Evaluating reasoning performance against baseline models

Getting Started

  • Visit the Hugging Face model page URL
  • Read the repository model card and README
  • Clone or download the repository
  • Install repository requirements and dependencies
  • Run provided example scripts or notebooks
  • Adapt the provided examples to your integration

Pricing

No pricing information provided; the model is open-sourced on Hugging Face.

Key Information

  • Category: Language Models
  • Type: AI Language Models Tool
Visit Official Website

Related Tools

Qwen2.5-7B

Qwen2.5-7B is a large language model designed for text generation, featuring improvements in coding, mathematics, instruction following, long text generation, and multilingual support. It supports context lengths up to 128K tokens and is intended for sophisticated NLP tasks.
DeepSeek-V3

An open-source language model from deepseek-ai offering efficient long-context inference with native sparse attention and support for multiple precisions.
Llama 3

Llama 3 is an open access large language model (LLM) released by Meta, available in various configurations (8B and 70B parameters) with capabilities for fine-tuning and integrations into platforms like Hugging Face, Google Cloud, and Amazon SageMaker.
UNfilteredAI-1B

A large-scale text generation model designed for creative and unconstrained content production without traditional filtering.
FLUX1.1 [pro]

A new text-to-image AI model capable of generating images six times faster than its predecessor, with higher quality, better prompt adherence, and more diversity in outputs. It includes a prompt upsampling feature that utilizes a language model to enhance prompts for improved image generation.
Shuttle-3

Shuttle-3 is a state-of-the-art language model designed for high-quality text generation, particularly suited for complex chat, multilingual communication, and reasoning tasks. It is fine-tuned from the Qwen-2.5-72b-Instruct model and designed to emulate high-quality prose similar to Claude 3 models.