Instructions to use PawanKrd/CosmosRP-8k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PawanKrd/CosmosRP-8k with Transformers:

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

pipe = pipeline("text-generation", model="PawanKrd/CosmosRP-8k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PawanKrd/CosmosRP-8k")
model = AutoModelForCausalLM.from_pretrained("PawanKrd/CosmosRP-8k")
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

vLLM

How to use PawanKrd/CosmosRP-8k with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PawanKrd/CosmosRP-8k

SGLang

How to use PawanKrd/CosmosRP-8k 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 "PawanKrd/CosmosRP-8k" \
    --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": "PawanKrd/CosmosRP-8k",
		"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 "PawanKrd/CosmosRP-8k" \
        --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": "PawanKrd/CosmosRP-8k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PawanKrd/CosmosRP-8k with Docker Model Runner:
```
docker model run hf.co/PawanKrd/CosmosRP-8k
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Hey there!

Welcome to CosmosRP – your new best friend for all things roleplay! This LLM is built specifically to make your roleplaying sessions more immersive, whether you're into fantasy, sci-fi, or historical reenactments. CosmosRP gets into the thick of the story, understands images, and responds in a way that keeps the adventure rolling.

What’s Cool About CosmosRP

Tailored for Roleplay: Responses are crafted to be engaging and spot-on for roleplay scenarios.
Image Understanding: Can look at images and integrate what it sees into the narrative.
Easy to Use: Uses the same API structure as OpenAI, so if you’re familiar with that, you’re good to go.
Free Access: Our API is free to use and doesn’t require an API key.

How to Access CosmosRP (8k Context Length)

Want to dive in? Use our API:

Base URL: https://api.pawan.krd/cosmosrp/v1 (can be used as like OpenAI reverse proxy)

For direct HTTP requests use : https://api.pawan.krd/cosmosrp/v1/chat/completions

Accessing CosmosRP-Pro (16k Context Length)

Our Patreon supporters will get access to CosmosRP-Pro which have 16k context length, you can join our Discord community for more info.

Example API Request

Here’s how you can chat with CosmosRP using the OpenAI API structure:

import requests

url = "https://api.pawan.krd/cosmosrp/v1/chat/completions"
headers = {
    "Content-Type": "application/json"
}
data = {
    "model": "cosmosrp",
    "messages": [
        {"role": "system", "content": "You are a fantasy world dungeon master."},
        {"role": "user", "content": "Describe the entrance of the ancient cave."}
    ]
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Join our Community

Come hang out with us on Discord! Chat with other roleplayers, share your stories, and get the latest updates.

Discord

If you like to support me:

Patreon

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

PawanKrd
/

CosmosRP-8k