Instructions to use Gryphe/Pantheon-10.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gryphe/Pantheon-10.7b with Transformers:

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

pipe = pipeline("text-generation", model="Gryphe/Pantheon-10.7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gryphe/Pantheon-10.7b")
model = AutoModelForCausalLM.from_pretrained("Gryphe/Pantheon-10.7b")
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 Gryphe/Pantheon-10.7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gryphe/Pantheon-10.7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gryphe/Pantheon-10.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Gryphe/Pantheon-10.7b

SGLang

How to use Gryphe/Pantheon-10.7b 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 "Gryphe/Pantheon-10.7b" \
    --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": "Gryphe/Pantheon-10.7b",
		"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 "Gryphe/Pantheon-10.7b" \
        --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": "Gryphe/Pantheon-10.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Gryphe/Pantheon-10.7b with Docker Model Runner:
```
docker model run hf.co/Gryphe/Pantheon-10.7b
```

Expert saturation and "ensuring smartness"

by karan4d - opened Feb 14, 2024

Discussion

karan4d

Feb 14, 2024

Curious about this snippet in the card:

Effort was put into ensuring that the smartness of Nous Hermes 2 remained unaffected while also allowing the user to apply a pantheon of personalities to act as 'skins' of a sort.

Would love some insight into reproducibility here. We've just recently started playing with MergeMonster.

Gryphe

Owner Feb 14, 2024

Oh, it's nowhere near as impressive as it sounds! I mainly ensured that the system prompts were simple yet distinct and that the resulting dialogue included character names.

My theory is that with those two steps the entire model is less likely to be influenced by the influx of new training data due to how "specific" the data becomes.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment