Itachi-42/loomstack-qwen-4b-sft-prompted

TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Apr 26, 2026Architecture:Transformer Cold

Itachi-42/loomstack-qwen-4b-sft-prompted is a 4 billion parameter language model, fine-tuned from unsloth/qwen3-4b-unsloth-bnb-4bit using the TRL framework. This model is specifically optimized for instruction following and conversational tasks, leveraging its SFT training procedure. With a 32768 token context length, it is well-suited for applications requiring detailed responses based on user prompts.

Loading preview...

Model Overview

Itachi-42/loomstack-qwen-4b-sft-prompted is a 4 billion parameter language model, fine-tuned from the unsloth/qwen3-4b-unsloth-bnb-4bit base model. This model was developed by Itachi-42 and trained using the TRL library with a Supervised Fine-Tuning (SFT) procedure.

Key Capabilities

  • Instruction Following: Optimized for generating responses based on explicit user instructions.
  • Conversational AI: Designed to handle interactive prompts and produce coherent, contextually relevant text.
  • Efficient Fine-tuning: Built upon a base model that leverages unsloth for efficient training, making it suitable for deployment in resource-constrained environments.

Training Details

The model underwent Supervised Fine-Tuning (SFT) to enhance its ability to follow prompts effectively. The training utilized specific framework versions:

  • TRL: 0.24.0
  • Transformers: 5.5.0
  • Pytorch: 2.10.0
  • Datasets: 4.3.0
  • Tokenizers: 0.22.2

Good For

  • Chatbots and Virtual Assistants: Generating human-like responses to user queries.
  • Content Generation: Creating text based on specific prompts or scenarios.
  • Prototyping: Quickly developing applications that require a capable, instruction-tuned language model.