Instructions to use Lambent/cosmoem-8x1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lambent/cosmoem-8x1B with Transformers:

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

pipe = pipeline("text-generation", model="Lambent/cosmoem-8x1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Lambent/cosmoem-8x1B")
model = AutoModelForMultimodalLM.from_pretrained("Lambent/cosmoem-8x1B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Lambent/cosmoem-8x1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lambent/cosmoem-8x1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lambent/cosmoem-8x1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Lambent/cosmoem-8x1B

SGLang

How to use Lambent/cosmoem-8x1B 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 "Lambent/cosmoem-8x1B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lambent/cosmoem-8x1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Lambent/cosmoem-8x1B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lambent/cosmoem-8x1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Lambent/cosmoem-8x1B with Docker Model Runner:
```
docker model run hf.co/Lambent/cosmoem-8x1B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

An untrained precursor MoE created from Cosmo using mergekit.

Gate routing initialized using prompt hidden state method. Five are based on the visualized topic clusters of Cosmopedia data, three are task-oriented.

Degenerate layers were 0, 1, and 2. Expert gates for layers 0, 1, and 2 have been randomly initialized to with luck mitigate this.

Downloads last month: 2

Safetensors

Model size

10B params

Tensor type

F32

Model tree for Lambent/cosmoem-8x1B

Adapters

1 model

Quantizations

1 model

Lambent
/

cosmoem-8x1B

Model tree for Lambent/cosmoem-8x1B

Dataset used to train Lambent/cosmoem-8x1B