qgallouedec/rick-qwen2.5-3b-sft-v2
The qgallouedec/rick-qwen2.5-3b-sft-v2 is a 3.1 billion parameter causal language model, fine-tuned from Qwen/Qwen2.5-3B-Instruct. Developed by qgallouedec, this model has been trained using the TRL framework with Supervised Fine-Tuning (SFT) to enhance its conversational capabilities. It is designed for general text generation tasks, particularly excelling in instruction-following scenarios with a context length of 32768 tokens.
Loading preview...
Overview
The qgallouedec/rick-qwen2.5-3b-sft-v2 is a 3.1 billion parameter causal language model, built upon the robust Qwen/Qwen2.5-3B-Instruct architecture. This model has undergone Supervised Fine-Tuning (SFT) using the TRL framework, developed by qgallouedec, to optimize its performance for instruction-following and general text generation tasks.
Key Capabilities
- Instruction Following: Enhanced through SFT, making it suitable for conversational agents and task-oriented prompts.
- Text Generation: Capable of generating coherent and contextually relevant text based on user input.
- Large Context Window: Supports a context length of 32768 tokens, allowing for processing and generating longer sequences of text.
Training Details
The model was trained using the SFT method within the TRL framework. The specific versions of the frameworks used include TRL 1.5.1, Transformers 5.10.2, Pytorch 2.7.1, Datasets 5.0.0, and Tokenizers 0.22.2.
Usage
Developers can easily integrate this model into their applications using the Hugging Face transformers library. It is compatible with AutoModelForCausalLM and AutoTokenizer for straightforward deployment in Python environments.