Text Generation
Transformers
Safetensors
GGUF
English
grt
geometric-rotation-transformer
causal-lm
rotational
Instructions to use MatterWaveAI/grt-20m-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MatterWaveAI/grt-20m-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MatterWaveAI/grt-20m-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("MatterWaveAI/grt-20m-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use MatterWaveAI/grt-20m-base with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf MatterWaveAI/grt-20m-base:F32 # Run inference directly in the terminal: llama cli -hf MatterWaveAI/grt-20m-base:F32
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf MatterWaveAI/grt-20m-base:F32 # Run inference directly in the terminal: llama cli -hf MatterWaveAI/grt-20m-base:F32
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf MatterWaveAI/grt-20m-base:F32 # Run inference directly in the terminal: ./build/bin/llama cli -hf MatterWaveAI/grt-20m-base:F32
Use Docker
docker model run hf.co/MatterWaveAI/grt-20m-base:F32
- Llama new
- LM Studio
- Jan
- vLLM
How to use MatterWaveAI/grt-20m-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MatterWaveAI/grt-20m-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MatterWaveAI/grt-20m-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MatterWaveAI/grt-20m-base:F32
- SGLang
How to use MatterWaveAI/grt-20m-base 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 "MatterWaveAI/grt-20m-base" \ --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": "MatterWaveAI/grt-20m-base", "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 "MatterWaveAI/grt-20m-base" \ --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": "MatterWaveAI/grt-20m-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Ollama
How to use MatterWaveAI/grt-20m-base with Ollama:
ollama run hf.co/MatterWaveAI/grt-20m-base:F32
- Unsloth Desktop
- Docker Model Runner
How to use MatterWaveAI/grt-20m-base with Docker Model Runner:
docker model run hf.co/MatterWaveAI/grt-20m-base:F32
- Lemonade
How to use MatterWaveAI/grt-20m-base with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MatterWaveAI/grt-20m-base:F32
Run and chat with the model
lemonade run user.grt-20m-base-F32
List all available models
lemonade list
- Atomic Chat
Archive untouched NeurIPS submission GRT-20M-Base checkpoint and zero-shot SLM-Bench baseline
9f377d7 verified Download eval_results.json from MatterWaveAI/grt-20m-base: direct link, hf CLI and curl.
- Browser
- Download file 2.58 kB
-
https://huggingface.co/MatterWaveAI/grt-20m-base/resolve/main/eval_results.json
- Command line
-
hf download hf://MatterWaveAI/grt-20m-base/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/MatterWaveAI/grt-20m-base/resolve/main/eval_results.json
2.58 kB
| { | |
| "model_id": "MatterWaveAI/grt-20m-base", | |
| "architecture": "GRTForCausalLM", | |
| "stored_parameters": 16730869, | |
| "non_embedding_parameters": 10280869, | |
| "dense_equiv_parameters": 22237440, | |
| "nn_linear_layers": 0, | |
| "pretraining": { | |
| "corpus": [ | |
| "OptimalScale/ClimbMix", | |
| "wikimedia/wikipedia", | |
| "tiiuae/falcon-refinedweb", | |
| "HuggingFaceFW/fineweb-edu", | |
| "HuggingFaceTB/cosmopedia", | |
| "nvidia/Nemotron-Pretraining-Dataset-sample", | |
| "HuggingFaceTB/finemath" | |
| ], | |
| "steps": 158000, | |
| "optimizer": "PairAdam", | |
| "train_loss": 2.114 | |
| }, | |
| "slm_bench_zero_shot": { | |
| "benchmark_suite": "SLM-Bench (9 Multiple-Choice Tasks + GSM8K Perplexity)", | |
| "evaluation_harness": "grt-slm-bench (training/slm_bench.py)", | |
| "mc_macro_average_accuracy": 0.3916, | |
| "pair_adam_mc_macro_average_accuracy": 0.3863, | |
| "random_macro_average": 0.3556, | |
| "tasks": { | |
| "boolq": { | |
| "split": "validation", | |
| "n_eval": 3270, | |
| "random": 0.5, | |
| "zero_shot_acc": 0.6217, | |
| "pair_adam_acc": 0.5343 | |
| }, | |
| "piqa": { | |
| "split": "validation", | |
| "n_eval": 1838, | |
| "random": 0.5, | |
| "zero_shot_acc": 0.5397, | |
| "pair_adam_acc": 0.5337 | |
| }, | |
| "winogrande": { | |
| "split": "validation", | |
| "n_eval": 1267, | |
| "random": 0.5, | |
| "zero_shot_acc": 0.5193, | |
| "pair_adam_acc": 0.5241 | |
| }, | |
| "qnli": { | |
| "split": "validation", | |
| "n_eval": 1000, | |
| "random": 0.5, | |
| "zero_shot_acc": 0.505, | |
| "pair_adam_acc": 0.557 | |
| }, | |
| "openbookqa": { | |
| "split": "test", | |
| "n_eval": 500, | |
| "random": 0.25, | |
| "zero_shot_acc": 0.342, | |
| "pair_adam_acc": 0.256 | |
| }, | |
| "hellaswag": { | |
| "split": "validation", | |
| "n_eval": 1000, | |
| "random": 0.25, | |
| "zero_shot_acc": 0.287, | |
| "pair_adam_acc": 0.318 | |
| }, | |
| "arc_easy": { | |
| "split": "test", | |
| "n_eval": 2376, | |
| "random": 0.25, | |
| "zero_shot_acc": 0.2643, | |
| "pair_adam_acc": 0.2685 | |
| }, | |
| "arc_challenge": { | |
| "split": "test", | |
| "n_eval": 1172, | |
| "random": 0.25, | |
| "zero_shot_acc": 0.2534, | |
| "pair_adam_acc": 0.2543 | |
| }, | |
| "commonsenseqa": { | |
| "split": "validation", | |
| "n_eval": 1221, | |
| "random": 0.2, | |
| "zero_shot_acc": 0.1916, | |
| "pair_adam_acc": 0.231 | |
| }, | |
| "gsm8k": { | |
| "split": "test", | |
| "n_eval": 500, | |
| "zero_shot_ppl": 60.12, | |
| "pair_adam_ppl": 12.52 | |
| } | |
| } | |
| } | |
| } | |