Instructions to use efficiency-learning/muon-gradientMatching with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use efficiency-learning/muon-gradientMatching with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("efficiency-learning/muon-gradientMatching", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download full_muon_lr0.005/config.json from efficiency-learning/muon-gradientMatching: direct link, hf CLI and curl.
- Browser
- Download file 1.31 kB
-
https://huggingface.co/efficiency-learning/muon-gradientMatching/resolve/main/full_muon_lr0.005/config.json
- Command line
-
hf download hf://efficiency-learning/muon-gradientMatching/full_muon_lr0.005/config.json
-
curl -L -o config.json https://huggingface.co/efficiency-learning/muon-gradientMatching/resolve/main/full_muon_lr0.005/config.json
1.31 kB
| { | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "float32", | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 896, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4864, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 24, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 14, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.15.1", | |
| "use_cache": true, | |
| "use_mrope": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |