how3751/Planner_3B_1.1
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Apr 15, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
how3751/Planner_3B_1.1 is a 3.1 billion parameter Qwen2.5-based instruction-tuned causal language model developed by how3751. Finetuned using Unsloth and Huggingface's TRL library, it offers a 32,768 token context length. This model is optimized for efficient performance, having been trained 2x faster, making it suitable for general instruction-following tasks.
Loading preview...
Model Overview
how3751/Planner_3B_1.1 is a 3.1 billion parameter instruction-tuned language model, developed by how3751. It is based on the Qwen2.5 architecture and features a substantial context length of 32,768 tokens, allowing it to process extensive inputs and generate comprehensive responses.
Key Capabilities
- Efficient Training: This model was finetuned using Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
- Qwen2.5 Foundation: Leveraging the Qwen2.5 base model, it inherits robust language understanding and generation capabilities.
- Instruction Following: As an instruction-tuned model, it is designed to accurately interpret and execute user commands and prompts.
Good For
- Applications requiring a balance of performance and efficiency.
- General instruction-following tasks where a large context window is beneficial.
- Developers looking for a Qwen2.5-based model with optimized training characteristics.