Instructions to use MC7ever/spark-darwin-6way with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MC7ever/spark-darwin-6way with Transformers:

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

pipe = pipeline("text-generation", model="MC7ever/spark-darwin-6way", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MC7ever/spark-darwin-6way", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MC7ever/spark-darwin-6way with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MC7ever/spark-darwin-6way"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MC7ever/spark-darwin-6way",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MC7ever/spark-darwin-6way

SGLang

How to use MC7ever/spark-darwin-6way 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 "MC7ever/spark-darwin-6way" \
    --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": "MC7ever/spark-darwin-6way",
		"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 "MC7ever/spark-darwin-6way" \
        --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": "MC7ever/spark-darwin-6way",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MC7ever/spark-darwin-6way with Docker Model Runner:
```
docker model run hf.co/MC7ever/spark-darwin-6way
```

spark-darwin-6way

Darwin uniform-soup merge (convex per-layer-block combination) of 6 Spark2.5-4B donors, all verified 290/290 tensors, identical shapes:

sriq-ai/sriq-spark-v1.4 (reasoning traces)
hcnote/Spark-X2.5-4B-Writing-EP1 (writing EP1)
hcnote/SparkMuse-4B (writing final)
soyaakinohara/Spark-X2.5-4B-Heretic (refusal-attenuated)
Takenoko12345678/Spark-X2.5-4B-Japanese (Japanese)
OceanLabs/Ocean-1-4B (general/agentic)

Method: theta_M = sum_i w_i theta_i, uniform w, 38 layer-block groups. Evo search over the genome comes next; this is the generation-0 baseline.

Verified specs: 36 layers, hidden 2560, intermediate 10240, 16 heads / 4 KV, vocab 131072, 290 tensors, ~4.11B. Full program plan: https://github.com/shadyuwugurl/spark-pipeline (SPARK_PLAN.md).

Needs transformers==5.17.0 + trust_remote_code=True. Custom code note: modeling_spark.py carries two compat shims vs stock (mask kwarg rename, dropped cache_position); config.json rope_parameters rewritten validator-clean with identical theta/factor values.

Eval battery in progress (hellaswag/arc_challenge/mmlu x200); numbers land here.

Downloads last month: 433

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for MC7ever/spark-darwin-6way

OceanLabs/Ocean-1-4B

Takenoko12345678/Spark-X2.5-4B-Japanese

hcnote/Spark-X2.5-4B-Writing-EP1

hcnote/SparkMuse-4B

soyaakinohara/Spark-X2.5-4B-Heretic

sriq-ai/sriq-spark-v1.4

Merge model

this model