Instructions to use DedeProGames/LowOnMind-1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DedeProGames/LowOnMind-1M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DedeProGames/LowOnMind-1M", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DedeProGames/LowOnMind-1M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DedeProGames/LowOnMind-1M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DedeProGames/LowOnMind-1M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DedeProGames/LowOnMind-1M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DedeProGames/LowOnMind-1M
- SGLang
How to use DedeProGames/LowOnMind-1M 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/LowOnMind-1M" \ --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/LowOnMind-1M", "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/LowOnMind-1M" \ --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/LowOnMind-1M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DedeProGames/LowOnMind-1M with Docker Model Runner:
docker model run hf.co/DedeProGames/LowOnMind-1M
Added to Neo Open SLM Leaderboard
Hey! Wanted to let you know that we’ve just added LowOnMind-1M and LowOnMind-300k to the Neo Open SLM Leaderboard.
Love seeing the progress on these models! You can see their rankings and full breakdown here: https://huggingface.co/spaces/AtomixLabs/Neo-Open-SLM-Leaderboard
The stolen slm leaderboard
The stolen slm leaderboard
Just wanted to let you know, the entire codebase was rewritten from scratch. And let's not start arguing here.
Also, following people across other creators' model cards to drop petty one liners is not it. Let's respect the author and keep this thread focused on celebrating their model release.
Yeah, and I didn't know yet now I know
That’s alright — but I think the issue can be declared resolved — no “stolen” (if you can call it that, that’s a whole other debate) code is there anymore.
@Datdanboi25 — I think we can leave this whole debacle behind us?
Yeah if he's rewritten the code and doing his own benchmarks, don't see an issue. Only real remaining one is refusing takedown requests but idrc.