lewtun/carbon-14b-sft-smoke-20260805-124457

TEXT GENERATIONPricing:Input $0.48 / Output $0.96Concurrent Unit Cost:1Model Size:14BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 5, 2026Architecture:Transformer Featherless Exclusive Cold

The lewtun/carbon-14b-sft-smoke-20260805-124457 is a 14 billion parameter instruction-tuned language model, fine-tuned from HuggingFaceBio/Qwen3-14B-Instruct-Mid using the TRL framework. This model is designed for general text generation tasks, leveraging its base architecture and supervised fine-tuning to produce coherent and contextually relevant responses. It is suitable for applications requiring a robust conversational AI or text completion capabilities.

Loading preview...

Model Overview

lewtun/carbon-14b-sft-smoke-20260805-124457 is a 14 billion parameter language model that has been supervised fine-tuned (SFT) from the HuggingFaceBio/Qwen3-14B-Instruct-Mid base model. The fine-tuning process utilized the TRL (Transformers Reinforcement Learning) framework, specifically version 1.10.0.dev0, indicating a focus on enhancing instruction-following capabilities.

Key Capabilities

  • Instruction Following: The model is fine-tuned to respond to user instructions, making it suitable for interactive applications.
  • Text Generation: Capable of generating coherent and contextually appropriate text based on given prompts.
  • Base Model Heritage: Benefits from the strong foundational capabilities of the Qwen3-14B-Instruct-Mid architecture.

Training Details

The model was trained using the SFT method, which typically involves training on a dataset of instruction-response pairs to align the model's output with human preferences and instructions. The training environment included:

  • TRL: 1.10.0.dev0
  • Transformers: 5.13.0.dev0
  • PyTorch: 2.11.0
  • Datasets: 5.0.0
  • Tokenizers: 0.22.2

Good For

  • General-purpose conversational AI: Responding to user queries and engaging in dialogue.
  • Text completion and generation: Creating various forms of text content.
  • Prototyping: Quickly setting up language model-powered applications that require instruction-tuned capabilities.