Question Answering
Transformers
Safetensors
grt
extractive-qa
squad
rotational-transformer
givens-rotations
clifford-algebra
matterwave
Instructions to use MatterWaveAI/grt-30m-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MatterWaveAI/grt-30m-qa with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="MatterWaveAI/grt-30m-qa")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForQuestionAnswering model = AutoModelForQuestionAnswering.from_pretrained("MatterWaveAI/grt-30m-qa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Release MatterWaveAI/grt-30m-qa (100% rotational head + 8-way geometric optimizer ablation)
92454d2 verified Download config.json from MatterWaveAI/grt-30m-qa: direct link, hf CLI and curl.
- Browser
- Download file 1.32 kB
-
https://huggingface.co/MatterWaveAI/grt-30m-qa/resolve/main/config.json
- Command line
-
hf download hf://MatterWaveAI/grt-30m-qa/config.json
-
curl -L -o config.json https://huggingface.co/MatterWaveAI/grt-30m-qa/resolve/main/config.json
1.32 kB
| { | |
| "angle_init_scale": 0.1, | |
| "architectures": [ | |
| "GRTForQuestionAnswering" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "coupling_init_mode": "diagonal", | |
| "coupling_init_scale": 0.01, | |
| "dtype": "float32", | |
| "eos_token_id": 151643, | |
| "ffn_n_experts": 0, | |
| "ffn_n_rotations": 21, | |
| "hidden_size": 256, | |
| "id2label": { | |
| "0": "SPAN_START", | |
| "1": "SPAN_END" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "label2id": { | |
| "SPAN_END": 1, | |
| "SPAN_START": 0 | |
| }, | |
| "learnable_residual_gates": true, | |
| "learnable_rope": true, | |
| "log_magnitude_init": 0.0, | |
| "max_position_embeddings": 2048, | |
| "model_type": "grt", | |
| "mor_delta_scale": 0.5, | |
| "mor_mode": "direct", | |
| "mor_router_mode": "rotational", | |
| "mor_split_routers": false, | |
| "mor_top_k": null, | |
| "n_mixer_rotations": 1, | |
| "n_qkv_rotations": 11, | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 12, | |
| "num_labels": 2, | |
| "output_scale_init": 30.0, | |
| "pad_token_id": 151643, | |
| "peri_ln": false, | |
| "phase_init_scale": 0.1, | |
| "pos_freq_base": 10000.0, | |
| "residual_gate_mode": "bounded_depth", | |
| "residual_norm_mode": "none", | |
| "rope_placement": "stream", | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.21.0.dev0", | |
| "use_cache": false, | |
| "vocab_size": 151669 | |
| } | |