Instructions to use movaxbx/OpenHermes-Emojitron-001 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use movaxbx/OpenHermes-Emojitron-001 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="movaxbx/OpenHermes-Emojitron-001")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("movaxbx/OpenHermes-Emojitron-001")
model = AutoModelForMultimodalLM.from_pretrained("movaxbx/OpenHermes-Emojitron-001")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use movaxbx/OpenHermes-Emojitron-001 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "movaxbx/OpenHermes-Emojitron-001"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "movaxbx/OpenHermes-Emojitron-001",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/movaxbx/OpenHermes-Emojitron-001

SGLang

How to use movaxbx/OpenHermes-Emojitron-001 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "movaxbx/OpenHermes-Emojitron-001" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "movaxbx/OpenHermes-Emojitron-001",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "movaxbx/OpenHermes-Emojitron-001" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "movaxbx/OpenHermes-Emojitron-001",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use movaxbx/OpenHermes-Emojitron-001 with Docker Model Runner:
```
docker model run hf.co/movaxbx/OpenHermes-Emojitron-001
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenHermes-Emojitron-001

🧑‍🎓📜🔄🌌➡️🗣️🌠🔮🖊️👀🤝🔄🧩🛠️👂📡🔐🌟

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 😊 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

Example Outputs
Benchmark Results
Prompt Format
Quantized Models

Example Outputs

Geography knowlege:

in what country is london

🇬🇧

Chat about food:

what country has the best food

🤔🌎🍽️

1️⃣🇮🇳

2️⃣🇯🇵

3️⃣🇺🇸

4️⃣🇪🇸

5️⃣🇫🇷

Talk about movies:

tell me a time travel story about a delorean

🛸🚗🕰️👨‍🔬🔍📅1985👴🚗💭🔜🌌😱💡💼🔢🔜📅1955🚗👨‍👩‍👧‍👦👀🔜🌉🕰️💥🌀🚗🕰️🔂📅1985👨‍🔬🎉

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 🕰️

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for movaxbx/OpenHermes-Emojitron-001

Base model

mistralai/Mistral-7B-v0.1

Finetuned

teknium/OpenHermes-2.5-Mistral-7B

Finetuned

(85)

this model

Quantizations

3 models

movaxbx
/

OpenHermes-Emojitron-001