OpenHermes-Emojitron-001

image/png

๐Ÿง‘โ€๐ŸŽ“๐Ÿ“œ๐Ÿ”„๐ŸŒŒโžก๏ธ๐Ÿ—ฃ๏ธ๐ŸŒ ๐Ÿ”ฎ๐Ÿ–Š๏ธ๐Ÿ‘€๐Ÿค๐Ÿ”„๐Ÿงฉ๐Ÿ› ๏ธ๐Ÿ‘‚๐Ÿ“ก๐Ÿ”๐ŸŒŸ

Model description

OpenHermes-Emojitron-001 is a state of the art Emoji Fine-tune, based on the OpenHermes 2.5 model.

It only speaks in emoji. Mostly. If using for chat, start it off with a nice ๐Ÿ˜Š to get going.

Huge thank you to Teknium and Mistral for a wonderful model.

Follow all my updates in ML and AI on Twitter: https://twitter.com/mov_axbx

Table of Contents

  1. Example Outputs
  2. Benchmark Results
  3. Prompt Format
  4. Quantized Models

Example Outputs

Geography knowlege:

in what country is london

๐Ÿ‡ฌ๐Ÿ‡ง

Chat about food:

what country has the best food

๐Ÿค”๐ŸŒŽ๐Ÿฝ๏ธ

1๏ธโƒฃ๐Ÿ‡ฎ๐Ÿ‡ณ

2๏ธโƒฃ๐Ÿ‡ฏ๐Ÿ‡ต

3๏ธโƒฃ๐Ÿ‡บ๐Ÿ‡ธ

4๏ธโƒฃ๐Ÿ‡ช๐Ÿ‡ธ

5๏ธโƒฃ๐Ÿ‡ซ๐Ÿ‡ท

Talk about movies:

tell me a time travel story about a delorean

๐Ÿ›ธ๐Ÿš—๐Ÿ•ฐ๏ธ๐Ÿ‘จโ€๐Ÿ”ฌ๐Ÿ”๐Ÿ“…1985๐Ÿ‘ด๐Ÿš—๐Ÿ’ญ๐Ÿ”œ๐ŸŒŒ๐Ÿ˜ฑ๐Ÿ’ก๐Ÿ’ผ๐Ÿ”ข๐Ÿ”œ๐Ÿ“…1955๐Ÿš—๐Ÿ‘จโ€๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ๐Ÿ‘€๐Ÿ”œ๐ŸŒ‰๐Ÿ•ฐ๏ธ๐Ÿ’ฅ๐ŸŒ€๐Ÿš—๐Ÿ•ฐ๏ธ๐Ÿ”‚๐Ÿ“…1985๐Ÿ‘จโ€๐Ÿ”ฌ๐ŸŽ‰

Benchmark Results

There are no benchmarks for emoji models. Maybe someone can create one. EmojiBench 5K let's gooooooo

Prompt Format

OpenHermes-Emojitron-001 uses ChatML as the prompt format, just like Open Hermes 2.5

It also appears to handle Mistral format great. Especially since I used that for the finetune (oops)

Quantized Models:

Coming soon if TheBloke thinks this is worth his ๐Ÿ•ฐ๏ธ

Downloads last month
52
Safetensors
Model size
7.24B params
Tensor type
BF16
ยท
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for movaxbx/OpenHermes-Emojitron-001

Finetuned
(72)
this model
Quantizations
2 models