Instructions to use aloobun/CosmicBun-8B-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aloobun/CosmicBun-8B-DPO with Transformers:

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

pipe = pipeline("text-generation", model="aloobun/CosmicBun-8B-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aloobun/CosmicBun-8B-DPO")
model = AutoModelForCausalLM.from_pretrained("aloobun/CosmicBun-8B-DPO")
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 aloobun/CosmicBun-8B-DPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/aloobun/CosmicBun-8B-DPO

SGLang

How to use aloobun/CosmicBun-8B-DPO 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 "aloobun/CosmicBun-8B-DPO" \
    --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": "aloobun/CosmicBun-8B-DPO",
		"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 "aloobun/CosmicBun-8B-DPO" \
        --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": "aloobun/CosmicBun-8B-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use aloobun/CosmicBun-8B-DPO with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aloobun/CosmicBun-8B-DPO to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aloobun/CosmicBun-8B-DPO to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aloobun/CosmicBun-8B-DPO to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="aloobun/CosmicBun-8B-DPO",
    max_seq_length=2048,
)

Docker Model Runner
How to use aloobun/CosmicBun-8B-DPO with Docker Model Runner:
```
docker model run hf.co/aloobun/CosmicBun-8B-DPO
```

CosmicBun-8B-DPO

"Arthur, he's dead!" I cried.

"Yes, of course he is," Arthur said numbly. He was staring with wide, haunted eyes at the wrecked receiver. "Gorrel listened to a colossal mind, a super-brain of space that didn't want him eavesdropping on it, and that ordered him to destroy the receiver and then die."

"A super-brain of space?" I exclaimed, "But what — where —" "

ARTHUR stumbled to a window, flung it open and pointed up. with a trembling hand at the starry, sky.

"It's up there!" he cried, and as he saw by my dazed stare that I did not understand, he added fiercely, "Didn't you see that the last wavelength Gorrel listened to, the thought-waves of the super-brain, was exactly .001 Angstroms? The exact wave-length of cosmic rays!"

"Cosmic rays?" I cried. "Then cosmic rays are really the thought waves of the super-brain? But they can't be — it's been proved that cosmic rays emanate from the stars of our galaxy."

"They do!" Arthur cried. "But the stars are only atoms in larger space, and in that larger space the star-atoms could combine to form living matter, thinking matter, couldn't they?

"Our galaxy, a mass of star-atoms gathered together into living, thinking matter — our galaxy is the superbrain!"

Short-Wave Madness, by Robert Castle.

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

F16

Model tree for aloobun/CosmicBun-8B-DPO

Base model

aloobun/CosmicBun-8B

Finetuned

(1)

this model

Merges

1 model