lhpku20010120/Omni-Edu-27B

VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 16, 2026License:otherArchitecture:Transformer0.0K Featherless Exclusive Cold

The lhpku20010120/Omni-Edu-27B model is a 27 billion parameter language model fine-tuned from Qwen/Qwen3.8-27B. It was specifically trained on the Omni-Edu-70K dataset, suggesting an optimization for educational or knowledge-based applications. With a context length of 32768 tokens, it is designed for processing extensive textual information relevant to its specialized training domain.

Loading preview...

Omni-Edu-27B: A Specialized Qwen3.8 Fine-tune

Omni-Edu-27B is a 27 billion parameter language model developed by lhpku20010120. It is a fine-tuned version of the Qwen/Qwen3.8-27B base model, specifically adapted through training on the Omni-Edu-70K dataset.

Key Characteristics

  • Base Model: Qwen/Qwen3.8-27B
  • Parameter Count: 27 billion parameters
  • Context Length: 32768 tokens, enabling the processing of long inputs.
  • Specialized Training: Fine-tuned on the Omni-Edu-70K dataset, indicating a focus on educational content or knowledge-intensive tasks.

Training Details

The model was trained with the following hyperparameters:

  • Learning Rate: 5e-06
  • Batch Size: 1 (train), 8 (eval) with 8 gradient accumulation steps, leading to a total effective batch size of 128.
  • Optimizer: ADAMW_TORCH_FUSED
  • Epochs: 3.0
  • Frameworks: Transformers 5.2.0, Pytorch 2.10.0, Datasets 4.0.0, Tokenizers 0.22.2.

Potential Use Cases

Given its specialized training on an educational dataset, Omni-Edu-27B is likely well-suited for applications requiring deep understanding or generation of educational content, academic assistance, or knowledge retrieval within specific domains.