Not-For-All-Audiences

Instructions to use Khetterman/Kosmos-8B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Khetterman/Kosmos-8B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Khetterman/Kosmos-8B-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Khetterman/Kosmos-8B-v1")
model = AutoModelForCausalLM.from_pretrained("Khetterman/Kosmos-8B-v1", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Khetterman/Kosmos-8B-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Khetterman/Kosmos-8B-v1

SGLang

How to use Khetterman/Kosmos-8B-v1 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 "Khetterman/Kosmos-8B-v1" \
    --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": "Khetterman/Kosmos-8B-v1",
		"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 "Khetterman/Kosmos-8B-v1" \
        --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": "Khetterman/Kosmos-8B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Khetterman/Kosmos-8B-v1 with Docker Model Runner:
```
docker model run hf.co/Khetterman/Kosmos-8B-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Kosmos-8B-v1

The serenity of infinity is not the end.

This is an interesting merge of 14 cool models, created using mergekit. Enjoy exploring :)

Merge Details

Method

This model was merged using the multistep process and remerge with some model variations for best result.

Models

The following models were included in the merge:

Configuration

The following YAML configurations was used to produce this model:

# Cursed-UnalignedCosmicSaiga-8B-v1
models:
  - model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA
  - model: aloobun/CosmicBun-8B-DPO
  - model: IlyaGusev/saiga_llama3_8b
merge_method: model_stock
base_model: Khetterman/CursedMatrix-8B-v9
dtype: bfloat16

# Cursed-BlueRainbowMaid-8B-v1
models:
  - model: v000000/L3-8B-BlueSerpentine
  - model: invisietch/L3.1-EtherealRainbow-v1.0-rc1-8B
  - model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
merge_method: model_stock
base_model: Khetterman/CursedMatrix-8B-v9
dtype: bfloat16

# Cursed-AverageLunaFusion-8B-v1
models:
  - model: jeiku/Average_Normie_v3.69_8B
  - model: Casual-Autopsy/L3-Luna-8B
  - model: ZeroXClem/Llama3.1-TheiaFire-DarkFusion-8B
merge_method: model_stock
base_model: Khetterman/CursedMatrix-8B-v9
dtype: bfloat16

# InfectedKosmos-8B-v1
models:
  - model: F:/Cursed-UnalignedCosmicSaiga-8B-v1
  - model: F:/Cursed-BlueRainbowMaid-8B-v1
  - model: F:/Cursed-AverageLunaFusion-8B-v1
merge_method: model_stock
base_model: Khetterman/CursedMatrix-8B-v9
dtype: bfloat16

# ZeroArkana-A
models:
  - model: ZeroXClem/L3SAO-Mix-SuperHermes-NovaPurosani-8B
    parameters:
      weight:  [0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50]
      density: [0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50]
  - model: Arkana08/LexiMaid-L3-8B
    parameters:
      weight:  [0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50]
      density: [0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50]
merge_method: della
parameters:
  epsilon: 0.1
  lambda:  1.0
base_model: F:/InfectedKosmos-8B-v1
dtype: bfloat16

# ZeroArkana-B
models:
  - model: ZeroXClem/Llama-3-Aetheric-Hermes-Lexi-Smaug-8B
    parameters:
      weight:  [0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50]
      density: [0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50]
  - model: Arkana08/Mythorica-L3-8B
    parameters:
      weight:  [0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50]
      density: [0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50, 0.65, 0.75, 0.80, 0.75, 0.65, 0.50, 0.35, 0.25, 0.20, 0.25, 0.35, 0.50]
merge_method: della
parameters:
  epsilon: 0.1
  lambda:  1.0
base_model: F:/InfectedKosmos-8B-v1
dtype: bfloat16

# Kosmos-8B-v1
models:
  - model: F:/ZeroArkana-A
  - model: F:/ZeroArkana-B
merge_method: model_stock
base_model: F:/InfectedKosmos-8B-v1
dtype: bfloat16