Instructions to use Tilo15/cosmic-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tilo15/cosmic-2 with Transformers:

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

pipe = pipeline("text-generation", model="Tilo15/cosmic-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tilo15/cosmic-2")
model = AutoModelForCausalLM.from_pretrained("Tilo15/cosmic-2", 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]:]))

PEFT
How to use Tilo15/cosmic-2 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Tilo15/cosmic-2 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Tilo15/cosmic-2:IQ1_M
# Run inference directly in the terminal:
llama cli -hf Tilo15/cosmic-2:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Tilo15/cosmic-2:IQ1_M
# Run inference directly in the terminal:
llama cli -hf Tilo15/cosmic-2:IQ1_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Tilo15/cosmic-2:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf Tilo15/cosmic-2:IQ1_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Tilo15/cosmic-2:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Tilo15/cosmic-2:IQ1_M

Use Docker

docker model run hf.co/Tilo15/cosmic-2:IQ1_M

LM Studio
Jan

vLLM

How to use Tilo15/cosmic-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tilo15/cosmic-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tilo15/cosmic-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tilo15/cosmic-2:IQ1_M

SGLang

How to use Tilo15/cosmic-2 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 "Tilo15/cosmic-2" \
    --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": "Tilo15/cosmic-2",
		"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 "Tilo15/cosmic-2" \
        --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": "Tilo15/cosmic-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Tilo15/cosmic-2 with Ollama:
```
ollama run hf.co/Tilo15/cosmic-2:IQ1_M
```

Unsloth Studio

How to use Tilo15/cosmic-2 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 Tilo15/cosmic-2 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 Tilo15/cosmic-2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Tilo15/cosmic-2 to start chatting

Docker Model Runner
How to use Tilo15/cosmic-2 with Docker Model Runner:
```
docker model run hf.co/Tilo15/cosmic-2:IQ1_M
```

Lemonade

How to use Tilo15/cosmic-2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Tilo15/cosmic-2:IQ1_M

Run and chat with the model

lemonade run user.cosmic-2-IQ1_M

List all available models

lemonade list

Atomic Chat

@@ -34,3 +34,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 ggml-model-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 ggml-model-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+cosmic-2-00001-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+cosmic-2-00002-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+cosmic-2-00003-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+cosmic-2-00004-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+cosmic-2-00005-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+cosmic-2-00006-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+cosmic-2-00007-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+cosmic-2-00008-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+cosmic-2-00009-of-00009.gguf filter=lfs diff=lfs merge=lfs -text

Tilo15
/

cosmic-2

add splits

+version https://git-lfs.github.com/spec/v1
+oid sha256:95c0e37a203d3761a88ff08eb7b2d49142ca20a00f6be30c583c9ff4164cd063
+size 499207744

+version https://git-lfs.github.com/spec/v1
+oid sha256:650139edc94615af1c030fdc307c3a59cc4135d73ddb055efd0cdfc257a38958
+size 498731200

+version https://git-lfs.github.com/spec/v1
+oid sha256:20a42a1434b35d4adbeb810829fda23434e641a00906555f42223bf0043db725
+size 490899744

+version https://git-lfs.github.com/spec/v1
+oid sha256:b14eaed43ff718b8d5ab00b08e3a67e3ba3e0e252caeba730443a257e1ca2685
+size 490866912

+version https://git-lfs.github.com/spec/v1
+oid sha256:f75e91ec719b3858dae99b0888431534c54145a0053b7185fe6107f4aa24b6ef
+size 499270208

+version https://git-lfs.github.com/spec/v1
+oid sha256:08fea44d829780025a1f49b80c282547bdab78cd7e007771e0d77aadef1b81bd
+size 500303904

+version https://git-lfs.github.com/spec/v1
+oid sha256:288f9fc7373724bfee3d9646dd376fb99f6f587b772202fc07f5c57ec44febdd
+size 179373088

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@