Instructions to use Gryphe/Pantheon-RP-1.0-8b-Llama-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gryphe/Pantheon-RP-1.0-8b-Llama-3 with Transformers:

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

pipe = pipeline("text-generation", model="Gryphe/Pantheon-RP-1.0-8b-Llama-3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gryphe/Pantheon-RP-1.0-8b-Llama-3")
model = AutoModelForCausalLM.from_pretrained("Gryphe/Pantheon-RP-1.0-8b-Llama-3", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gryphe/Pantheon-RP-1.0-8b-Llama-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gryphe/Pantheon-RP-1.0-8b-Llama-3"
# 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-RP-1.0-8b-Llama-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Gryphe/Pantheon-RP-1.0-8b-Llama-3

SGLang

How to use Gryphe/Pantheon-RP-1.0-8b-Llama-3 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-RP-1.0-8b-Llama-3" \
    --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-RP-1.0-8b-Llama-3",
		"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-RP-1.0-8b-Llama-3" \
        --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-RP-1.0-8b-Llama-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Gryphe/Pantheon-RP-1.0-8b-Llama-3 with Docker Model Runner:
```
docker model run hf.co/Gryphe/Pantheon-RP-1.0-8b-Llama-3
```

Excellent. Some feedback.

by aaronday3 - opened Jun 8, 2024

Discussion

aaronday3

Jun 8, 2024

Excellent model! A breath of fresh air amidst a sea of these GPT slopped Assistant models that are uncreative asf.

I'm really curious as to how you did it, like what makes this model more creative and more human-like. I'll admit the worst part of the model is that it doesn't seem to be super smart with following through the context, however its so creative, like its immensely creative even more than MythoMax which is crazy to me.

I'm guessing making it smart, coherent and creative will likely require an entire team of people so I suppose it's a really great model as it is as most of the creativity comes from hallucinations.

Great work!

Joseph717171

Jun 20, 2024

@aaronday3 Perhaps you can use its outputs to craft synthetic datasets? 🤔

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