Instructions to use Ppoyaa/LuminRP-7B-128k-v0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ppoyaa/LuminRP-7B-128k-v0.5 with Transformers:

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

pipe = pipeline("text-generation", model="Ppoyaa/LuminRP-7B-128k-v0.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ppoyaa/LuminRP-7B-128k-v0.5")
model = AutoModelForCausalLM.from_pretrained("Ppoyaa/LuminRP-7B-128k-v0.5", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ppoyaa/LuminRP-7B-128k-v0.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ppoyaa/LuminRP-7B-128k-v0.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ppoyaa/LuminRP-7B-128k-v0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ppoyaa/LuminRP-7B-128k-v0.5

SGLang

How to use Ppoyaa/LuminRP-7B-128k-v0.5 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 "Ppoyaa/LuminRP-7B-128k-v0.5" \
    --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": "Ppoyaa/LuminRP-7B-128k-v0.5",
		"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 "Ppoyaa/LuminRP-7B-128k-v0.5" \
        --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": "Ppoyaa/LuminRP-7B-128k-v0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ppoyaa/LuminRP-7B-128k-v0.5 with Docker Model Runner:
```
docker model run hf.co/Ppoyaa/LuminRP-7B-128k-v0.5
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LuminRP-7B-128k-v0.5

Description

LuminRP-7B-128k-v0.5 is a merge of various models that specializes in roleplaying. This model is an upgrade to Ppoyaa/LuminRP-7B-128k-v0.4 to fix the slight issue and improve the ERP and overall performance.

Based on my testing, this model outperforms the previous v0.4 version in both RP and ERP and would recommend this version over it.

This is the final version of the 7B variant as I'm pretty satisfied with it's performance as a 7B model.

Quants

By mradermacher:

Static GGUF: mradermacher/LuminRP-7B-128k-v0.5-GGUF

SillyTavern

Template: Alpaca, ChatML, and Mistral should be okay.

Instruct Mode: On

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Ppoyaa/LuminRP-7B-128k-v0.5"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Merge Details Below:

See Merge Config

ChaoticNeutrals/BuRP_7B
Endevor/InfinityRP-v1-7B
Nitral-AI/Kunocchini-7b-128k-test
core-3/kuno-royale-v2-7b
KatyTheCutie/LemonadeRP-4.5.3
grimjim/kukulemon-7B
MaziyarPanahi/Calme-7B-Instruct-v0.9
icefog72/WestIceLemonTeaRP-32k-7b
crestf411/daybreak-kunoichi-2dpo-7b
Undi95/Mistral-RP-0.1-7B

Downloads last month: 13

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Ppoyaa/LuminRP-7B-128k-v0.5

Quantizations

1 model

Collection including Ppoyaa/LuminRP-7B-128k-v0.5

LuminRP Models

Collection

Models based on Mistral that excels in roleplaying. • 3 items • Updated May 17, 2024 • 1