Instructions to use Gryphe/MythoMax-L2-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gryphe/MythoMax-L2-13b with Transformers:

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

pipe = pipeline("text-generation", model="Gryphe/MythoMax-L2-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gryphe/MythoMax-L2-13b")
model = AutoModelForCausalLM.from_pretrained("Gryphe/MythoMax-L2-13b", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gryphe/MythoMax-L2-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gryphe/MythoMax-L2-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gryphe/MythoMax-L2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Gryphe/MythoMax-L2-13b

SGLang

How to use Gryphe/MythoMax-L2-13b 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 "Gryphe/MythoMax-L2-13b" \
    --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": "Gryphe/MythoMax-L2-13b",
		"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 "Gryphe/MythoMax-L2-13b" \
        --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": "Gryphe/MythoMax-L2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Gryphe/MythoMax-L2-13b with Docker Model Runner:
```
docker model run hf.co/Gryphe/MythoMax-L2-13b
```

This model Rocks!

by nixudos - opened Aug 18, 2023

Discussion

nixudos

Aug 18, 2023

I just wanted to put my appreciation here for this amazing model!
I've tried quite a lot of 13B models, but this has turned out to be the winner. Good coherence, good reasoning skills and great for Character based chat!

I can recommend using the GGML q6 version found on TheBloke. And use Mirostat 2 setting with a tau of 5 and 0.1 in the last parameter.

I had some weirdness happening with the GPTQ model after a very long chat session, but that might have been because of wrong parameter settings.

JoggyMuffin

Aug 20, 2023

Mirostat is incredible with this model

joelkuiper

Sep 8, 2023

•

This comment has been hidden

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment