Instructions to use something-else/HF-rocm-rwkv-3B-48-2048-ctx16384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use something-else/HF-rocm-rwkv-3B-48-2048-ctx16384 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("something-else/HF-rocm-rwkv-3B-48-2048-ctx16384", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from something-else/HF-rocm-rwkv-3B-48-2048-ctx16384: direct link, hf CLI and curl.
- Browser
- Download file 418 Bytes
-
https://huggingface.co/something-else/HF-rocm-rwkv-3B-48-2048-ctx16384/resolve/main/config.json
- Command line
-
hf download hf://something-else/HF-rocm-rwkv-3B-48-2048-ctx16384/config.json
-
curl -L -o config.json https://huggingface.co/something-else/HF-rocm-rwkv-3B-48-2048-ctx16384/resolve/main/config.json
418 Bytes
| { | |
| "attention_hidden_size": 2048, | |
| "bos_token_id": 0, | |
| "context_length": 4096, | |
| "eos_token_id": 0, | |
| "head_size": 64, | |
| "hidden_size": 2048, | |
| "intermediate_size": null, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "rwkv5", | |
| "model_version": "5_2", | |
| "num_hidden_layers": 48, | |
| "rescale_every": 6, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.35.2", | |
| "use_cache": true, | |
| "vocab_size": 65536 | |
| } | |