Text Generation
RWKV
Japanese
English
Chinese
rwkv7
speculative-decoding
multi-token-prediction
mtp
draft-model
Instructions to use OpenMOSE/RWKV7-MTP-Exp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- RWKV
How to use OpenMOSE/RWKV7-MTP-Exp with RWKV:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download index.json from OpenMOSE/RWKV7-MTP-Exp: direct link, hf CLI and curl.
- Browser
- Download file 830 Bytes
-
https://huggingface.co/OpenMOSE/RWKV7-MTP-Exp/resolve/main/index.json
- Command line
-
hf download hf://OpenMOSE/RWKV7-MTP-Exp/index.json
-
curl -L -o index.json https://huggingface.co/OpenMOSE/RWKV7-MTP-Exp/resolve/main/index.json
830 Bytes
| { | |
| "format": "rwkv-mtp", | |
| "version": 1, | |
| "sidecars": [ | |
| { | |
| "base_model": "RWKV7-G1l-2.9B-20261031", | |
| "path": "RWKV7-G1l-2.9B-20261031", | |
| "hf_base": [ | |
| "RWKV/RWKV7-G1l-2.9B-20261031" | |
| ], | |
| "n_layer": 32, | |
| "n_embd": 2560, | |
| "fuse_layers": [ | |
| 9, | |
| 19 | |
| ], | |
| "trained_tokens": 999981056 | |
| }, | |
| { | |
| "base_model": "RWKV7-G1l-7.2B-20261031", | |
| "path": "RWKV7-G1l-7.2B-20261031", | |
| "hf_base": [ | |
| "RWKV/RWKV7-G1l-7.2B-20261031" | |
| ], | |
| "n_layer": 32, | |
| "n_embd": 4096, | |
| "fuse_layers": [ | |
| 9, | |
| 19 | |
| ], | |
| "trained_tokens": 999981056 | |
| }, | |
| { | |
| "base_model": "RWKV7-G1l-13.3B-20261031", | |
| "path": "RWKV7-G1l-13.3B-20261031", | |
| "hf_base": [ | |
| "RWKV/RWKV7-G1l-13.3B-20261031" | |
| ], | |
| "n_layer": 61, | |
| "n_embd": 4096, | |
| "fuse_layers": [ | |
| 17, | |
| 36 | |
| ], | |
| "trained_tokens": 999981056 | |
| } | |
| ] | |
| } |