Shellypeckie/student_qwen3_1p7b_clean4b_numseq_seq_kd
TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 24, 2026Architecture:Transformer Featherless Exclusive Cold
Shellypeckie/student_qwen3_1p7b_clean4b_numseq_seq_kd is a 1.7 billion parameter language model, fine-tuned from Qwen/Qwen3-1.7B using the TRL framework. This model is specifically trained for sequence-to-sequence tasks, focusing on numerical sequences and clean data. It is optimized for applications requiring precise handling and generation of structured numerical outputs.
Loading preview...
Model Overview
This model, student_qwen3_1p7b_clean4b_numseq_seq_kd, is a specialized variant of the Qwen3-1.7B architecture, featuring 1.7 billion parameters and a 32768-token context length. It has undergone supervised fine-tuning (SFT) using the TRL framework, indicating a focus on specific task performance rather than broad general-purpose capabilities.
Key Capabilities
- Specialized Fine-tuning: Built upon the Qwen/Qwen3-1.7B base model, it has been fine-tuned for particular sequence-to-sequence tasks.
- Numerical Sequence Handling: The model's naming suggests an optimization for processing and generating numerical sequences.
- Clean Data Focus: Training on "clean4b" data implies an emphasis on high-quality, structured input for improved output reliability.
Good For
- Specific Sequence-to-Sequence Tasks: Ideal for applications where the model needs to transform input sequences into structured output sequences, especially those involving numerical data.
- Research and Development: Useful for researchers exploring the impact of targeted fine-tuning on base models for niche applications.
- Controlled Data Environments: Best suited for use cases with well-defined and clean input data, leveraging its specialized training.