raulgdp/deepseek14b-acredita
TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kPublished:May 17, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
raulgdp/deepseek14b-acredita is a 14.8 billion parameter Qwen2-based causal language model developed by raulgdp, finetuned from unsloth/deepseek-r1-distill-qwen-14b. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster finetuning. It is designed for general text generation tasks, leveraging its efficient training methodology.
Loading preview...
Model Overview
raulgdp/deepseek14b-acredita is a 14.8 billion parameter language model, finetuned by raulgdp. It is based on the Qwen2 architecture and was specifically trained from the unsloth/deepseek-r1-distill-qwen-14b base model.
Key Characteristics
- Architecture: Qwen2-based, a causal language model.
- Parameter Count: 14.8 billion parameters.
- Context Length: Supports a context length of 32768 tokens.
- Training Efficiency: This model was finetuned with Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
Potential Use Cases
- General Text Generation: Suitable for a wide range of text generation tasks due to its large parameter count and Qwen2 base.
- Efficient Deployment: Models trained with Unsloth often benefit from optimized performance, making them potentially efficient for inference.
- Further Finetuning: Can serve as a strong base for additional domain-specific finetuning, leveraging its efficient training heritage.