Instructions to use OmnicromsBrain/NeuralStar_AlphaWriter_4x7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OmnicromsBrain/NeuralStar_AlphaWriter_4x7b with Transformers:

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

pipe = pipeline("text-generation", model="OmnicromsBrain/NeuralStar_AlphaWriter_4x7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OmnicromsBrain/NeuralStar_AlphaWriter_4x7b")
model = AutoModelForCausalLM.from_pretrained("OmnicromsBrain/NeuralStar_AlphaWriter_4x7b")
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 Settings

vLLM

How to use OmnicromsBrain/NeuralStar_AlphaWriter_4x7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OmnicromsBrain/NeuralStar_AlphaWriter_4x7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OmnicromsBrain/NeuralStar_AlphaWriter_4x7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OmnicromsBrain/NeuralStar_AlphaWriter_4x7b

SGLang

How to use OmnicromsBrain/NeuralStar_AlphaWriter_4x7b 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 "OmnicromsBrain/NeuralStar_AlphaWriter_4x7b" \
    --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": "OmnicromsBrain/NeuralStar_AlphaWriter_4x7b",
		"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 "OmnicromsBrain/NeuralStar_AlphaWriter_4x7b" \
        --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": "OmnicromsBrain/NeuralStar_AlphaWriter_4x7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OmnicromsBrain/NeuralStar_AlphaWriter_4x7b with Docker Model Runner:
```
docker model run hf.co/OmnicromsBrain/NeuralStar_AlphaWriter_4x7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

NeuralStar_AlphaWriter_4x7b

I was blown away by the writing results I was getting from mlabonne/Beyonder-4x7B-v3 while writing in NovelCrafter.

Inspired by his LLM Course and fueled by his LazyMergeKit. I couldnt help but wonder what a writing model would be like if all 4 “experts” excelled in creative writing.

I present NeuralStar-AlphaWriter-4x7b:

NeuralStar_AlphaWriter_4x7b is a Mixture of Experts (MoE) made with the following models using LazyMergekit:

⚡ Quantized Models

Special thanks to MRadermacher for the Static and iMatrx quantized models

.GGUF https://huggingface.co/mradermacher/NeuralStar_AlphaWriter_4x7b-GGUF

iMatrix https://huggingface.co/mradermacher/NeuralStar_AlphaWriter_4x7b-i1-GGUF

Q4_K_M and Q5_K_M .gguf Here created with mlabonne/Autogguf

🧩 Configuration

base_model: mlabonne/AlphaMonarch-7B
experts:  
  - source_model: mlabonne/AlphaMonarch-7B
    positive_prompts: 
    - "chat"
    - "assistant"
    - "tell me"
    - "explain"
    - "I want"
  - source_model: FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B
    positive_prompts:
    - "edit"
    - "rewrite"
    - "evaluate"
    - "spelling"
    - "grammer"
  - source_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
    positive_prompts:
    - "storywriting"
    - "write"
    - "scene"
    - "prose"
    - "character"
  - source_model: OmnicromsBrain/NeuralStar-7b-Lazy
    positive_prompts:
    - "codex"
    - "plot"
    - "outline"
    - "scenebeat"
    - "count"

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "OmnicromsBrain/NeuralStar_AlphaWriter_4x7b"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.31
AI2 Reasoning Challenge (25-Shot)	70.22
HellaSwag (10-Shot)	88.31
MMLU (5-Shot)	64.60
TruthfulQA (0-shot)	71.70
Winogrande (5-shot)	82.00
GSM8k (5-shot)	63.00

Downloads last month: 12

Safetensors

Model size

24B params

Tensor type

F16

Model tree for OmnicromsBrain/NeuralStar_AlphaWriter_4x7b

FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B

OmnicromsBrain/NeuralStar-7b-Lazy

SanjiWatsuki/Kunoichi-DPO-v2-7B

mlabonne/AlphaMonarch-7B

Merge model

this model

Quantizations

2 models

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

70.220
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

88.310
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.600
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

71.700
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

82.000
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

63.000