Instructions to use nbeerbower/SuperBruphin-3x7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nbeerbower/SuperBruphin-3x7B with Transformers:

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

pipe = pipeline("text-generation", model="nbeerbower/SuperBruphin-3x7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nbeerbower/SuperBruphin-3x7B")
model = AutoModelForCausalLM.from_pretrained("nbeerbower/SuperBruphin-3x7B")
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 nbeerbower/SuperBruphin-3x7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nbeerbower/SuperBruphin-3x7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nbeerbower/SuperBruphin-3x7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nbeerbower/SuperBruphin-3x7B

SGLang

How to use nbeerbower/SuperBruphin-3x7B 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 "nbeerbower/SuperBruphin-3x7B" \
    --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": "nbeerbower/SuperBruphin-3x7B",
		"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 "nbeerbower/SuperBruphin-3x7B" \
        --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": "nbeerbower/SuperBruphin-3x7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nbeerbower/SuperBruphin-3x7B with Docker Model Runner:
```
docker model run hf.co/nbeerbower/SuperBruphin-3x7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SuperBruphin-3x7B

This is an experimental MoE model created using mergekit. (mixtral branch)

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: nbeerbower/bruphin-epsilon
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: nbeerbower/bruphin-epsilon
    positive_prompts:
        - "Tell a story."
  - source_model: FelixChao/WestSeverus-7B-DPO-v2
    positive_prompts:
        - "Solve this problem."
  - source_model: jondurbin/airoboros-m-7b-3.1.2
    positive_prompts:
        - "Write a letter."

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.75
AI2 Reasoning Challenge (25-Shot)	71.16
HellaSwag (10-Shot)	87.74
MMLU (5-Shot)	64.58
TruthfulQA (0-shot)	66.85
Winogrande (5-shot)	81.53
GSM8k (5-shot)	70.66

Downloads last month: 70

Safetensors

Model size

19B params

Tensor type

BF16

Model tree for nbeerbower/SuperBruphin-3x7B

Base model

PetroGPT/WestSeverus-7B-DPO-v2

Finetuned

(1)

this model

Quantizations

1 model

Evaluation results

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

71.160
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

87.740
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.580
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

66.850
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

81.530
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

70.660