3MPER0RR/DeepSeek-R1-Distill-Qwen-14B-3MPER0RR-abliterated

TEXT GENERATIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 12, 2026License:mitArchitecture:Transformer Open Weights Featherless Exclusive Cold

The 3MPER0RR/DeepSeek-R1-Distill-Qwen-14B-3MPER0RR-abliterated is an experimental 14.8 billion parameter language model, a modified version of the DeepSeek-R1-Distill-Qwen architecture. Developed by 3MPER0RR, this model features a 32768 token context length and is the result of specific trials and research. It is designed for general language tasks, leveraging its substantial parameter count and context window for robust performance.

Loading preview...

Model Overview

This model, named DeepSeek-R1-Distill-Qwen-14B-3MPER0RR-abliterated, is an experimental and modified version of the original DeepSeek-R1-Distill-Qwen architecture. Developed and researched by 3MPER0RR, it features 14.8 billion parameters and supports a context length of 32768 tokens. The model has undergone specific trials, indicated by "Trials: [200]", suggesting a focused development process.

Key Characteristics

  • Architecture: Based on the DeepSeek-R1-Distill-Qwen model.
  • Parameter Count: 14.8 billion parameters, offering significant capacity for complex language understanding and generation.
  • Context Length: A substantial 32768 tokens, enabling the processing of long inputs and maintaining coherence over extended conversations or documents.
  • Experimental Nature: This is an "abliterated" version, implying targeted modifications and research by 3MPER0RR to explore specific performance characteristics or optimizations.
  • License: Released under the MIT License, providing flexibility for use and distribution.

Use Cases

Given its large parameter count and extensive context window, this model is suitable for a variety of general-purpose language tasks, including:

  • Text Generation: Creating coherent and contextually relevant long-form content.
  • Complex Reasoning: Handling tasks that require understanding and processing large amounts of information.
  • Research and Experimentation: Ideal for developers and researchers interested in exploring modified LLM architectures and their performance implications.

Finetunes
1 models