---
license: mit
library_name: gguf
language:
- en
base_model:
- microsoft/DialoGPT-medium
pipeline_tag: text-generation
tags:
- conversational
- gguf
- quantization
- dialogpt
---

## DialoGPT-medium-GGUF

# ! WARNING: model may be broken. !

This repository contains the full suite of GGUF quantizations for [microsoft/DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium). 

DialoGPT is a large-scale pretrained dialogue response generation model. This version has been converted to GGUF format for use with `llama.cpp` and other compatible executors like LM Studio or GPT4All.

## Usage Instructions

### Using llama.cpp
```bash
./llama-cli -m DialoGPT-medium.Q4_K_M.gguf \
  -p "User: What is the secret to a happy life?\nBot:" \
  -n 128
```