abdoul-rz/qwen3-4b-sports-mix

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 7, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

abdoul-rz/qwen3-4b-sports-mix is a 4 billion parameter language model fine-tuned from Qwen/Qwen3-4B, specifically optimized for tasks related to the sports-mix dataset. This model leverages a 32768-token context length, making it suitable for processing extensive sports-related text. Its fine-tuning on a specialized dataset suggests enhanced performance for sports analytics, content generation, and information retrieval within the sports domain.

Loading preview...

Model Overview

This model, abdoul-rz/qwen3-4b-sports-mix, is a specialized language model built upon the Qwen/Qwen3-4B architecture. It features 4 billion parameters and supports a substantial context length of 32768 tokens, enabling it to handle detailed and lengthy inputs.

Key Capabilities

  • Specialized Domain Knowledge: Fine-tuned on the sports-mix dataset, this model is expected to exhibit enhanced understanding and generation capabilities for sports-related content.
  • Large Context Window: The 32768-token context length allows for processing extensive documents or conversations, which is beneficial for analyzing game reports, player statistics, or sports news articles.

Training Details

The model was trained with a learning rate of 5e-05 over 1 epoch, utilizing a total batch size of 128 across 4 GPUs. The training employed an AdamW optimizer with cosine learning rate scheduling and a warmup ratio of 0.1. This configuration aims to optimize performance within its target domain.

Good For

  • Sports Content Generation: Creating articles, summaries, or commentary related to various sports.
  • Sports Analytics: Processing and extracting insights from sports data and textual information.
  • Information Retrieval: Answering questions or finding specific details within large bodies of sports text.

Limitations

As a fine-tuned model, its primary strength lies within the sports domain. Performance on general-purpose tasks or domains outside of sports may not be as robust as broader base models.