datasysdev/Code1
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 13, 2025Architecture:Transformer Featherless Exclusive Warm
datasysdev/Code1 is a 0.8 billion parameter language model, fine-tuned from Qwen/Qwen3-0.6B using SFT with TRL. This model is designed for general text generation tasks, leveraging its compact architecture and 32768-token context length for efficient deployment and processing of longer inputs. Its primary use case is generating coherent and contextually relevant text based on user prompts.
Loading preview...
Overview
datasysdev/Code1 is a 0.8 billion parameter language model, fine-tuned from the Qwen/Qwen3-0.6B base model. This model was developed by datasysdev and trained using the SFT (Supervised Fine-Tuning) method with the TRL library. It is designed for efficient text generation tasks, offering a balance between model size and performance.
Key Capabilities
- General Text Generation: Capable of generating coherent and contextually relevant text based on diverse prompts.
- Efficient Deployment: Its compact 0.8B parameter size makes it suitable for applications requiring lower computational resources.
- Fine-tuned Performance: Leverages supervised fine-tuning to enhance its text generation abilities from the Qwen3-0.6B base.
Good For
- Applications requiring a lightweight yet capable language model for text generation.
- Scenarios where efficient inference and deployment are critical.
- Developers looking for a fine-tuned Qwen3-0.6B variant for specific text-based tasks.