Instructions to use kaanino/gpt-mha-SwiGLU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kaanino/gpt-mha-SwiGLU with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import GPT model = GPT.from_pretrained("kaanino/gpt-mha-SwiGLU", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from kaanino/gpt-mha-SwiGLU: direct link, hf CLI and curl.
- Browser
- Download file 359 Bytes
-
https://huggingface.co/kaanino/gpt-mha-SwiGLU/resolve/main/config.json
- Command line
-
hf download hf://kaanino/gpt-mha-SwiGLU/config.json
-
curl -L -o config.json https://huggingface.co/kaanino/gpt-mha-SwiGLU/resolve/main/config.json
359 Bytes
| { | |
| "activation_type": "swiglu", | |
| "architectures": [ | |
| "GPT" | |
| ], | |
| "dropout": 0.1, | |
| "dtype": "float32", | |
| "max_seq_length": 128, | |
| "model_type": "gpt", | |
| "n_embd": 64, | |
| "n_head": 4, | |
| "n_kv_head": 4, | |
| "n_layer": 6, | |
| "norm_type": "rmsnorm", | |
| "pos_enc_type": "relative", | |
| "transformers_version": "5.5.4", | |
| "use_cache": false, | |
| "vocab_size": 50257 | |
| } | |