RichardErkhov/Thamed-Chowdhury_-_qwen-2.5-7B-DPO-split1-16bit-full-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

qwen-2.5-7B-DPO-split1-16bit-full - GGUF

• —Model creator: https://huggingface.co/Thamed-Chowdhury/
• —Original model: https://huggingface.co/Thamed-Chowdhury/qwen-2.5-7B-DPO-split1-16bit-full/

Original model description: --- base_model: Thamed-Chowdhury/qwen-2.5-7B-DPO-split1-16bit-chunk12 tags:

• —text-generation-inference
• —transformers
• —unsloth
• —qwen2
• —trl
• —dpo license: apache-2.0 language:
• —en ---

Uploaded model

• —Developed by: Thamed-Chowdhury
• —License: apache-2.0
• —Finetuned from model : Thamed-Chowdhury/qwen-2.5-7B-DPO-split1-16bit-chunk12

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>