Instructions to use DedeProGames/DynamicMind-MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DedeProGames/DynamicMind-MoE with Transformers:

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

pipe = pipeline("text-generation", model="DedeProGames/DynamicMind-MoE", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("DedeProGames/DynamicMind-MoE", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DedeProGames/DynamicMind-MoE with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DedeProGames/DynamicMind-MoE

SGLang

How to use DedeProGames/DynamicMind-MoE 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 "DedeProGames/DynamicMind-MoE" \
    --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": "DedeProGames/DynamicMind-MoE",
		"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 "DedeProGames/DynamicMind-MoE" \
        --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": "DedeProGames/DynamicMind-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DedeProGames/DynamicMind-MoE with Docker Model Runner:
```
docker model run hf.co/DedeProGames/DynamicMind-MoE
```

Kindly asking for a SupraLabs compute GPU grant in Runpod

by LH-Tech-AI - opened about 9 hours ago

Discussion

LH-Tech-AI

about 9 hours ago

Hey there!
I saw that you're supporting BananaMind with compute and we're currently planning Supra3 family with four core models: 25M, 50M, 75M and 100M.
For the 75M and 100M models, we do not have enough money to pay the GPU cost for e.g. RTX 5090 or H100 on Runpod.
We kindly ask you if you'd like to support our work.
I already made a post about it here:
https://huggingface.co/posts/LH-Tech-AI/471515595964278

Tell me if you're interested 🤗

Thank you for your time.

DedeProGames

Owner about 4 hours ago

Sure! I just need to be invited to Supra Labs Org.

LH-Tech-AI

about 1 hour ago

Hey there! We really appreciate that and we're happy to hear that.
I invited you to our HF org - so you can join anytime.

Do you have discord? My name there: lh_tech_ai

Then we can talk there if you want.

We're still researching and writing code so it could be a few weeks to prepare it okay?

Thanks so much 🤗🙏

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