Instructions to use CultriX/MergeStage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CultriX/MergeStage1 with Transformers:

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

pipe = pipeline("text-generation", model="CultriX/MergeStage1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CultriX/MergeStage1")
model = AutoModelForCausalLM.from_pretrained("CultriX/MergeStage1")
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 CultriX/MergeStage1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CultriX/MergeStage1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CultriX/MergeStage1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CultriX/MergeStage1

SGLang

How to use CultriX/MergeStage1 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 "CultriX/MergeStage1" \
    --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": "CultriX/MergeStage1",
		"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 "CultriX/MergeStage1" \
        --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": "CultriX/MergeStage1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CultriX/MergeStage1 with Docker Model Runner:
```
docker model run hf.co/CultriX/MergeStage1
```

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using jpacifico/Chocolatine-2-14B-Instruct-v2.0.3 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

name: SuperMergedModel-v1
merge_method: model_stock
base_model: jpacifico/Chocolatine-2-14B-Instruct-v2.0.3  # Qwen-based
tokenizer_source: base  # Verify and update if needed
dtype: bfloat16
parameters:
  normalize: true
  rescale: false
  int8_mask: true
models:
  - model: arcee-ai/Virtuoso-Small-v2  # Qwen-based, IFEval focus
  - model: jpacifico/Chocolatine-2-14B-Instruct-v2.0b3  # Qwen-based, related to base
  - model: sometimesanotion/Qwenvergence-14B-v12-Prose-DS  # Qwen-based, good overall score
  - model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2  # Qwen-based, from Qwenvergence
  - model: oxyapi/oxy-1-small  # Qwen-based, from Qwenvergence
  - model: allura-org/TQ2.5-14B-Sugarquill-v1  # Qwen-based, from Qwenvergence
  - model: underwoods/medius-erebus-magnum-14b  # Qwen-based, from Qwenvergence
  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2  # Qwen-based, from Qwenvergence