MalvinasMan/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slimy_shrewd_whale

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Apr 21, 2025Architecture:Transformer Featherless Exclusive Cold

MalvinasMan/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slimy_shrewd_whale is a 0.5 billion parameter instruction-tuned language model, fine-tuned from Gensyn/Qwen2.5-0.5B-Instruct. This model leverages the GRPO training method, as introduced in the DeepSeekMath paper, to enhance its mathematical reasoning capabilities. With a 32768 token context length, it is optimized for tasks requiring robust mathematical problem-solving and logical deduction. It is suitable for applications needing a compact model with strong reasoning skills.

Loading preview...

Model Overview

This model, MalvinasMan/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slimy_shrewd_whale, is a 0.5 billion parameter instruction-tuned language model. It is a fine-tuned variant of the Gensyn/Qwen2.5-0.5B-Instruct base model, developed to improve specific reasoning capabilities.

Key Capabilities & Training

The primary differentiator of this model lies in its training methodology. It was fine-tuned using GRPO (Guided Reasoning Policy Optimization), a technique detailed in the research paper "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models" (arXiv:2402.03300). This method is designed to enhance a model's ability to perform complex mathematical reasoning and logical deduction.

  • Base Model: Gensyn/Qwen2.5-0.5B-Instruct
  • Parameter Count: 0.5 billion
  • Context Length: 32768 tokens
  • Training Method: GRPO, focused on mathematical reasoning
  • Frameworks: Trained with TRL (Transformer Reinforcement Learning), Transformers, PyTorch, Datasets, and Tokenizers.

Use Cases

Given its specialized training with GRPO, this model is particularly well-suited for:

  • Mathematical Problem Solving: Tasks requiring step-by-step mathematical reasoning.
  • Logical Deduction: Applications where precise logical inference is crucial.
  • Educational Tools: Assisting with math-related queries or generating explanations for mathematical concepts.
  • Resource-Constrained Environments: Its compact size (0.5B parameters) makes it efficient for deployment where computational resources are limited, while still offering enhanced reasoning capabilities.

Finetunes
1 models