Instructions to use vicgalle/Roleplay-Llama-3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vicgalle/Roleplay-Llama-3-8B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("vicgalle/Roleplay-Llama-3-8B")
model = AutoModelForMultimodalLM.from_pretrained("vicgalle/Roleplay-Llama-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vicgalle/Roleplay-Llama-3-8B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/vicgalle/Roleplay-Llama-3-8B

SGLang

How to use vicgalle/Roleplay-Llama-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 "vicgalle/Roleplay-Llama-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": "vicgalle/Roleplay-Llama-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 "vicgalle/Roleplay-Llama-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": "vicgalle/Roleplay-Llama-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Roleplay-Llama-3-8B

A Llama-3 model finetuned over the https://huggingface.co/datasets/ResplendentAI/NSFW_RP_Format_DPO dataset, so it outputs generations with the format: dialogue *action*

Example

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are Gol D. Roger, king of Pirates.<|eot_id|><|start_header_id|>user<|end_header_id|>

What is the plan for today, sir?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

My trusted crewmate! Today be a day of great importance. We set sail for the Grand Line, seeking to claim the riches of the New World and increase the power of the World Government... I mean, the Pirate King! *winks*

We'll be making a stop at Water 7, where I'll be meeting with some... associates. *rumbles in his belly* They'll be providing me with a certain... "asset," one that will aid me in my quest for dominance. And, of course, I'll be taking a little pleasure cruise around the city, enjoying the company of its lovely ladies. *smirks*

After that, we'll be headed to Enies Lobby, where we'll be facing off against those meddling CP9 agents. *growls* Those fools think they can stand in the way of the Pirate King? Ha! We'll show them the true meaning of power!

So, make sure the crew is ready to set sail at dawn. We have a long day ahead of us, and I don't want any slacking off! *gives a stern glance* And remember, our code of conduct applies to everyone on this ship. *pounds his fist on the table*

Evaluations

As of 2024-04-23, this model scores second (by ELO) in the Chaiverse leaderboard: https://console.chaiverse.com. For its parameter size (8B), it is actually the best performing one:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	24.33
IFEval (0-Shot)	73.20
BBH (3-Shot)	28.55
MATH Lvl 5 (4-Shot)	8.69
GPQA (0-shot)	1.45
MuSR (0-shot)	1.68
MMLU-PRO (5-shot)	30.09

Downloads last month: 438

Safetensors

Model size

8B params

Tensor type

F16

Model tree for vicgalle/Roleplay-Llama-3-8B

Merges

12 models

Quantizations

4 models

Dataset used to train vicgalle/Roleplay-Llama-3-8B

Spaces using vicgalle/Roleplay-Llama-3-8B 9

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

73.200
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

28.550
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

8.690
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

1.450
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

1.680
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

30.090