meathuggingface/DeepSeek-R1-API-Doc

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Mar 16, 2025License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The DeepSeek-R1-API-Doc is a 1.5 billion parameter Qwen2-based causal language model developed by meathuggingface. This model was fine-tuned from unsloth/deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit, leveraging Unsloth and Huggingface's TRL library for accelerated training. It is designed for general language generation tasks, offering efficient performance due to its optimized training process.

Loading preview...

Model Overview

The DeepSeek-R1-API-Doc is a 1.5 billion parameter language model based on the Qwen2 architecture, developed by meathuggingface. It was fine-tuned from the unsloth/deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit model.

Key Characteristics

  • Architecture: Qwen2-based causal language model.
  • Parameter Count: 1.5 billion parameters.
  • Training Optimization: Utilizes Unsloth and Huggingface's TRL library, enabling training at twice the speed compared to standard methods.
  • License: Released under the Apache-2.0 license.

Intended Use Cases

This model is suitable for various natural language processing tasks where a compact yet efficient language model is required. Its optimized training process makes it a good candidate for applications prioritizing faster iteration and deployment, particularly within environments that benefit from Unsloth's performance enhancements.

Finetunes
2 models