Instructions to use ananjayram/hana with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ananjayram/hana with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ananjayram/hana", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from ananjayram/hana: direct link, hf CLI and curl.
- Browser
- Download file 240 Bytes
-
https://huggingface.co/ananjayram/hana/resolve/main/config.json
- Command line
-
hf download hf://ananjayram/hana/config.json
-
curl -L -o config.json https://huggingface.co/ananjayram/hana/resolve/main/config.json
240 Bytes
| { | |
| "vocab_size": 50257, | |
| "block_size": 512, | |
| "d_model": 512, | |
| "n_layers": 8, | |
| "n_heads": 8, | |
| "use_moe": true, | |
| "num_experts": 8, | |
| "top_k": 2, | |
| "dense_ffn_dim": 1536, | |
| "expert_ffn_dim": 768, | |
| "dropout": 0.0 | |
| } |