huihui-ai/Qwen2.5-32B-Instruct-abliterated-SFT

Hugging Face
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kLicense:apache-2.0Architecture:Transformer0.0K Open Weights Warm

huihui-ai/Qwen2.5-32B-Instruct-abliterated-SFT is a 32.8 billion parameter instruction-tuned causal language model developed by huihui-ai. It is fine-tuned from the Qwen2.5-32B-Instruct-abliterated model using the Guilherme34_uncensor dataset. This model is designed for general conversational AI tasks, leveraging its instruction-following capabilities for diverse applications.

Loading preview...

Model Overview

huihui-ai/Qwen2.5-32B-Instruct-abliterated-SFT is a 32.8 billion parameter instruction-tuned language model developed by huihui-ai. It is built upon the Qwen2.5-32B-Instruct-abliterated base model and further fine-tuned using the huihui-ai/Guilherme34_uncensor dataset. This SFT (Supervised Fine-Tuning) process aims to enhance the model's ability to follow instructions and engage in helpful conversations.

Key Capabilities

  • Instruction Following: Optimized for understanding and executing user instructions.
  • Conversational AI: Designed to function as a helpful assistant in chat-based interactions.
  • Fine-tuned Performance: Leverages specific dataset for improved response generation.

Usage and Integration

The model can be easily integrated using the Hugging Face transformers library. It supports 4-bit quantization for efficient deployment and includes a custom text streamer for real-time output generation. The provided code snippet demonstrates how to load the model, set up the tokenizer, and run an interactive chat session, including handling user input and streaming responses.