Instructions to use Walmart-the-bag/MysticFusion-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Walmart-the-bag/MysticFusion-13B with Transformers:

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

pipe = pipeline("text-generation", model="Walmart-the-bag/MysticFusion-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Walmart-the-bag/MysticFusion-13B")
model = AutoModelForCausalLM.from_pretrained("Walmart-the-bag/MysticFusion-13B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Walmart-the-bag/MysticFusion-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Walmart-the-bag/MysticFusion-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Walmart-the-bag/MysticFusion-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Walmart-the-bag/MysticFusion-13B

SGLang

How to use Walmart-the-bag/MysticFusion-13B 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 "Walmart-the-bag/MysticFusion-13B" \
    --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": "Walmart-the-bag/MysticFusion-13B",
		"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 "Walmart-the-bag/MysticFusion-13B" \
        --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": "Walmart-the-bag/MysticFusion-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Walmart-the-bag/MysticFusion-13B with Docker Model Runner:
```
docker model run hf.co/Walmart-the-bag/MysticFusion-13B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MysticFusion-13B

YAML:

models:
  - model: KoboldAI/LLaMA2-13B-Tiefighter
    parameters:
      weight: 0.3
  - model: NeverSleep/Noromaid-13b-v0.1.1
    parameters:
      weight: 0.5
  - model: lmsys/vicuna-13b-v1.5
    parameters:
      weight: 0.2
merge_method: linear
dtype: float16

Usage:

This is meant to be story writing and basic instruction. More of story writing.

Prompt Template:

Alpaca

### Instruction:

### Response:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	59.31
AI2 Reasoning Challenge (25-Shot)	61.35
HellaSwag (10-Shot)	84.43
MMLU (5-Shot)	57.29
TruthfulQA (0-shot)	51.98
Winogrande (5-shot)	76.01
GSM8k (5-shot)	24.79