zxcd1/MyModel_xh
TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 8, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
MyModel_xh is a 7.6 billion parameter Qwen2 model developed by zxcd1, fine-tuned from unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It features a 32768 token context length and is optimized for efficient performance due to its training methodology.
Loading preview...
MyModel_xh Overview
MyModel_xh is a 7.6 billion parameter Qwen2-based language model developed by zxcd1. It was fine-tuned from the unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit model, leveraging the Unsloth library and Huggingface's TRL library for training. This approach allowed for a significant acceleration in the training process, achieving 2x faster training times.
Key Capabilities
- Efficient Training: Utilizes Unsloth and Huggingface TRL for optimized and faster fine-tuning.
- Qwen2 Architecture: Based on the robust Qwen2 model family.
- Context Length: Supports a substantial context window of 32768 tokens, suitable for processing longer inputs.
Good For
- Applications requiring a Qwen2-based model with a large context window.
- Use cases where efficient fine-tuning and deployment are critical.
- Developers looking for models trained with Unsloth for performance benefits.