mulasan/bistbot-deepseek-math-8b

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 23, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The mulasan/bistbot-deepseek-math-8b is an 8 billion parameter Llama-based model, finetuned by mulasan from unsloth/DeepSeek-R1-Distill-Llama-8B-bnb-4bit. This model was optimized for faster training using Unsloth and Huggingface's TRL library. It is designed for general language tasks, leveraging its Llama architecture and efficient finetuning process.

Loading preview...

Model Overview

The mulasan/bistbot-deepseek-math-8b is an 8 billion parameter language model, finetuned by mulasan. It is based on the Llama architecture, specifically finetuned from the unsloth/DeepSeek-R1-Distill-Llama-8B-bnb-4bit model.

Key Characteristics

  • Architecture: Llama-based, 8 billion parameters.
  • Finetuning: Developed using Unsloth and Huggingface's TRL library, enabling 2x faster training.
  • Origin: Finetuned from unsloth/DeepSeek-R1-Distill-Llama-8B-bnb-4bit.

Use Cases

This model is suitable for various general language processing tasks where an 8 billion parameter Llama-based model with efficient finetuning is beneficial. Its optimized training process suggests potential for applications requiring rapid iteration or deployment.

Finetunes
1 models