AmberYifan/capsd-qwen3-numina-Qwen3-4B-Base-math_random_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_random_b2000_s0 is a 4 billion parameter language model, fine-tuned from Qwen/Qwen3-4B-Base. This model is specifically optimized for mathematical and random number generation tasks, leveraging a specialized dataset for its training. It is designed for applications requiring robust performance in numerical reasoning and probabilistic outputs. The model has a context length of 32768 tokens.

Loading preview...

Model Overview

This model, AmberYifan/capsd-qwen3-numina-Qwen3-4B-Base-math_random_b2000_s0, is a fine-tuned variant of the Qwen3-4B-Base architecture, developed by AmberYifan. It features 4 billion parameters and supports a substantial 32768-token context length.

Key Characteristics

  • Base Model: Fine-tuned from Qwen/Qwen3-4B-Base.
  • Specialized Training: The model underwent fine-tuning on the capsd_Qwen3-4B-Base-n80000-numina__mix_math_random_b2000_s0 dataset.
  • Optimization Focus: Its training regimen suggests an optimization for tasks involving mathematical reasoning and random number generation.

Training Details

The fine-tuning process utilized the following hyperparameters:

  • Learning Rate: 1e-05
  • Batch Sizes: train_batch_size of 2, eval_batch_size of 8, with a gradient_accumulation_steps of 8, leading to a total_train_batch_size of 64.
  • Optimizer: AdamW with betas=(0.9, 0.999) and epsilon=1e-08.
  • Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
  • Epochs: Trained for 1 epoch.
  • Frameworks: Transformers 5.8.0, Pytorch 2.13.0+cu130, Datasets 4.0.0, Tokenizers 0.22.2.

Intended Use Cases

While specific use cases are not detailed in the original README, the specialized training on a "mix_math_random" dataset indicates its potential suitability for:

  • Applications requiring numerical problem-solving.
  • Tasks involving the generation or understanding of random sequences or probabilistic outcomes.
  • Scenarios where a compact 4B parameter model with enhanced mathematical capabilities is beneficial.

Finetunes
1 models