AmberYifan/capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b2000_s0

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 17, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

AmberYifan/capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b2000_s0 is a 4 billion parameter language model, fine-tuned from Qwen/Qwen3-4B-Base. This model is specifically optimized for mathematical tasks, having been fine-tuned on the capsd_Qwen3-4B-Base-n80000-numina__mix_math_ppl_b2000_s0 dataset. It features a context length of 32768 tokens and is designed for applications requiring strong mathematical reasoning capabilities.

Loading preview...

Model Overview

This model, AmberYifan/capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b2000_s0, is a specialized 4 billion parameter language model. It is a fine-tuned variant of the Qwen/Qwen3-4B-Base architecture, specifically enhanced for mathematical performance.

Key Capabilities & Training

  • Base Model: Fine-tuned from Qwen/Qwen3-4B-Base.
  • Parameter Count: 4 billion parameters.
  • Context Length: Supports a context window of 32768 tokens.
  • Specialization: Optimized for mathematical tasks through fine-tuning on the capsd_Qwen3-4B-Base-n80000-numina__mix_math_ppl_b2000_s0 dataset.
  • Training Details: The model underwent a single epoch of training with a learning rate of 1e-05, using a total batch size of 64 across 4 devices with gradient accumulation. The optimizer used was ADAMW_TORCH with a cosine learning rate scheduler.

Intended Use Cases

This model is particularly suited for applications and research focused on:

  • Mathematical Problem Solving: Tasks requiring numerical reasoning, equation solving, or mathematical text generation.
  • Quantitative Analysis: Scenarios where robust mathematical understanding is crucial.

Limitations

As per the provided information, specific intended uses and limitations require further detail. Users should conduct their own evaluations for specific applications.