AmberYifan/capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_cap_b4000_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-sciweb-stackexchange-Qwen3-4B-Base-science_cap_b4000_s0 is a 4 billion parameter language model, fine-tuned from Qwen/Qwen3-4B-Base. This model is specifically adapted using the capsd_Qwen3-4B-Base-n80000-sciweb-stackexchange__mix_science_cap_b4000_s0 dataset, suggesting a specialization in scientific web and StackExchange content. With a context length of 32768 tokens, it is designed for tasks requiring deep understanding and generation within scientific domains.

Loading preview...

Model Overview

This model, AmberYifan/capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_cap_b4000_s0, is a 4 billion parameter language model derived from the Qwen3-4B-Base architecture. It has been fine-tuned on a specialized dataset, capsd_Qwen3-4B-Base-n80000-sciweb-stackexchange__mix_science_cap_b4000_s0, indicating a focus on content from scientific web sources and StackExchange.

Key Training Details

  • Base Model: Qwen/Qwen3-4B-Base
  • Dataset: capsd_Qwen3-4B-Base-n80000-sciweb-stackexchange__mix_science_cap_b4000_s0
  • Learning Rate: 1e-05
  • Optimizer: ADAMW_TORCH
  • Epochs: 1
  • Context Length: 32768 tokens

Potential Use Cases

Given its fine-tuning on scientific web and StackExchange data, this model is likely suitable for applications requiring:

  • Understanding and generating text related to scientific topics.
  • Processing and summarizing information from technical forums and scientific articles.
  • Assisting with queries or content generation in scientific or academic contexts.