kamalmdev/DeepSeek-R1-Distill-Llama-8B-classification-merged

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 18, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The kamalmdev/DeepSeek-R1-Distill-Llama-8B-classification-merged is an 8 billion parameter Llama-based model, fine-tuned for classification tasks. Developed by kamalmdev, this model leverages the DeepSeek-R1-Distill architecture and was trained using Unsloth and Huggingface's TRL library for accelerated performance. It is designed for efficient and fast deployment in classification applications, offering a balance of size and specialized capability.

Loading preview...

Model Overview

The kamalmdev/DeepSeek-R1-Distill-Llama-8B-classification-merged is an 8 billion parameter Llama-based model specifically fine-tuned for classification tasks. It is built upon the unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit base model.

Key Characteristics

  • Architecture: Llama-based, leveraging the DeepSeek-R1-Distill framework.
  • Parameter Count: 8 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling a 2x faster training process.
  • Specialization: Optimized for classification tasks, making it suitable for applications requiring categorization or labeling.

Intended Use Cases

This model is particularly well-suited for developers and researchers focused on:

  • Text Classification: Categorizing documents, emails, or other textual data.
  • Sentiment Analysis: Determining the emotional tone of text.
  • Topic Modeling: Identifying the main subjects within a collection of texts.
  • Efficient Deployment: Its optimized training and moderate size make it a good candidate for applications where faster inference and reduced resource consumption are beneficial for classification tasks.