Instructions to use mookiezii/Discord-Hermes-3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mookiezii/Discord-Hermes-3-8B with Transformers:

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

pipe = pipeline("text-generation", model="mookiezii/Discord-Hermes-3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mookiezii/Discord-Hermes-3-8B")
model = AutoModelForMultimodalLM.from_pretrained("mookiezii/Discord-Hermes-3-8B")
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]:]))

HERMES

How to use mookiezii/Discord-Hermes-3-8B with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mookiezii/Discord-Hermes-3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mookiezii/Discord-Hermes-3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mookiezii/Discord-Hermes-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mookiezii/Discord-Hermes-3-8B

SGLang

How to use mookiezii/Discord-Hermes-3-8B 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 "mookiezii/Discord-Hermes-3-8B" \
    --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": "mookiezii/Discord-Hermes-3-8B",
		"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 "mookiezii/Discord-Hermes-3-8B" \
        --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": "mookiezii/Discord-Hermes-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mookiezii/Discord-Hermes-3-8B with Docker Model Runner:
```
docker model run hf.co/mookiezii/Discord-Hermes-3-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Discord-Hermes-3-8B

Model Description

This is a fine-tuned version of NousResearch/Hermes-3-Llama-3.1-8B, trained on a curated dataset built from a mixture of enhanced and original samples from mookiezi/Discord-Dialogues.

The training hyper-parameters and log are available here.

Sample Outputs

⚠️ Disclaimer: The first image is fictional dialogue.
It should not be interpreted as political advice, a statement of fact, or an endorsement of any kind.

Interfacing

An optimized Python script for interfacing is available here.

Windows

py interface.py

macOS

python3 interface.py

Linux

python3 interface.py

Downloads last month: 668

Safetensors

Model size

8B params

Tensor type

F16

Model tree for mookiezii/Discord-Hermes-3-8B

Base model

meta-llama/Llama-3.1-8B

Finetuned

NousResearch/Hermes-3-Llama-3.1-8B

Finetuned

(33)

this model

Quantizations

2 models

mookiezii
/

Discord-Hermes-3-8B