MycMycuH/DildoQwen2.5
MycMycuH/DildoQwen2.5 is a 1.5 billion parameter instruction-tuned causal language model, fine-tuned by MycMycuH from unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit. This model was trained using the TRL library with a context length of 32768 tokens. It is designed for general text generation tasks following instructions.
Loading preview...
Overview
MycMycuH/DildoQwen2.5 is a 1.5 billion parameter instruction-tuned language model, derived from the unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit base model. It has been fine-tuned using the TRL (Transformer Reinforcement Learning) library, specifically employing a Supervised Fine-Tuning (SFT) training procedure.
Key Capabilities
- Instruction Following: Designed to generate text based on user instructions, as demonstrated by its instruction-tuned nature.
- Text Generation: Capable of general text generation tasks, suitable for conversational AI or creative writing prompts.
- Context Length: Supports a substantial context window of 32768 tokens, allowing for processing and generating longer sequences of text.
Training Details
The model's training leveraged PEFT (Parameter-Efficient Fine-Tuning) version 0.18.1, TRL version 0.24.0, Transformers version 5.5.0, Pytorch version 2.10.0+cu128, and Datasets version 4.3.0. This setup indicates a focus on efficient fine-tuning methods to adapt the base Qwen2.5 model for specific instruction-following capabilities.