Instructions to use jan-hq/supermario-slerp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jan-hq/supermario-slerp with Transformers:

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

pipe = pipeline("text-generation", model="jan-hq/supermario-slerp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jan-hq/supermario-slerp")
model = AutoModelForCausalLM.from_pretrained("jan-hq/supermario-slerp")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jan-hq/supermario-slerp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jan-hq/supermario-slerp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jan-hq/supermario-slerp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jan-hq/supermario-slerp

SGLang

How to use jan-hq/supermario-slerp 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 "jan-hq/supermario-slerp" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jan-hq/supermario-slerp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "jan-hq/supermario-slerp" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jan-hq/supermario-slerp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Jan - Discord

Model Description

This model uses the Slerp merge method from 2 models:

base model: Mistral-7B-v0.1

The yaml config file for this model is here:

slices:
  - sources:
      - model: Weyaxi/Seraph-7B
        layer_range: [0, 32]

      - model: AIDC-ai-business/Marcoroni-7B-v3
        layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

Run this model

You can run this model using Jan Desktop on Mac, Windows, or Linux.

Jan is an open source, ChatGPT alternative that is:

💻 100% offline on your machine: Your conversations remain confidential, and visible only to you.
🗂️ An Open File Format: Conversations and model settings stay on your computer and can be exported or deleted at any time.
🌐 OpenAI Compatible: Local server on port 1337 with OpenAI compatible endpoints
🌍 Open Source & Free: We build in public; check out our Github

About Jan

Jan believes in the need for an open-source AI ecosystem and is building the infra and tooling to allow open-source AIs to compete on a level playing field with proprietary ones.

Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life.

Jan Model Merger

This is a test project for merging models.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here.

Metric	Value
Avg.	72.32
ARC (25-shot)	68.94
HellaSwag (10-shot)	86.58
MMLU (5-shot)	64.93
TruthfulQA (0-shot)	60.11
Winogrande (5-shot)	81.29
GSM8K (5-shot)	72.1

Acknowlegement

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.32
AI2 Reasoning Challenge (25-Shot)	68.94
HellaSwag (10-Shot)	86.58
MMLU (5-Shot)	64.93
TruthfulQA (0-shot)	60.11
Winogrande (5-shot)	81.29
GSM8k (5-shot)	72.10

Downloads last month: 76

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for jan-hq/supermario-slerp

Quantizations

1 model

Collection including jan-hq/supermario-slerp

Supermario

Collection

This is a test project for new merging methods (DARE, TIES, SLERP). • 5 items • Updated Jul 10, 2024

Evaluation results

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

68.940
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

86.580
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.930
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

60.110
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

81.290
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

72.100