Instructions to use TroyDoesAI/MermaidMixtral-2x7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TroyDoesAI/MermaidMixtral-2x7b with Transformers:

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

pipe = pipeline("text-generation", model="TroyDoesAI/MermaidMixtral-2x7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TroyDoesAI/MermaidMixtral-2x7b")
model = AutoModelForCausalLM.from_pretrained("TroyDoesAI/MermaidMixtral-2x7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TroyDoesAI/MermaidMixtral-2x7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TroyDoesAI/MermaidMixtral-2x7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TroyDoesAI/MermaidMixtral-2x7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TroyDoesAI/MermaidMixtral-2x7b

SGLang

How to use TroyDoesAI/MermaidMixtral-2x7b 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 "TroyDoesAI/MermaidMixtral-2x7b" \
    --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": "TroyDoesAI/MermaidMixtral-2x7b",
		"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 "TroyDoesAI/MermaidMixtral-2x7b" \
        --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": "TroyDoesAI/MermaidMixtral-2x7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TroyDoesAI/MermaidMixtral-2x7b with Docker Model Runner:
```
docker model run hf.co/TroyDoesAI/MermaidMixtral-2x7b
```

Request: DOI

by parth0209 - opened Apr 1, 2024

Discussion

parth0209

Apr 1, 2024

can you help me how can i merge your models

TroyDoesAI

Owner Apr 1, 2024

What part do you need help with? MergeKit should work no problem with this model. The 2x6.5b being an odd size might not be so easy but the 2x7B should be able to merge fine.

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