The EmbeddingRWKV Model
Project description
The RWKV-X Language Model
https://github.com/howard-hou/EmbeddingRWKV
# !!! set these before import RWKV !!!
import os
os.environ["RWKV_CUDA_ON"] = '0' # '1' to compile CUDA kernel (10x faster), requires c++ compiler & cuda libraries
from rwkv_emb
EOS_INDEX = 65535
# download models: to be announced
model = RWKV_X(model_path='path-to-model', strategy='cpu fp32')
# !!! model.forward(tokens, state) will modify state in-place !!!
emb, state = model.forward([187, 510, 1563, 310, 247, EOS_INDEX], None)
print(emb.detach().cpu().numpy()) # get logits
emb, state = model.forward([187, 510], None)
emb, state = model.forward([1563], state) # RNN has state (use deepcopy to clone states)
emb, state = model.forward([310, 247, EOS_INDEX], state)
print(emb.detach().cpu().numpy()) # same result as above
print('\n')
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
rwkv_emb-0.0.1.tar.gz
(393.6 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
rwkv_emb-0.0.1-py3-none-any.whl
(392.9 kB
view details)
File details
Details for the file rwkv_emb-0.0.1.tar.gz.
File metadata
- Download URL: rwkv_emb-0.0.1.tar.gz
- Upload date:
- Size: 393.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ecb86cdc5f73b1f6e9a383cb5854a12acf45e4eccd3e270189140e68480dfe9a
|
|
| MD5 |
1074ab443f0fc91d66e5b106da2c8aec
|
|
| BLAKE2b-256 |
151d8e3276cdb302580bcdca6a4bb256bc8acee91362581ba7a22e6970ca1c94
|
File details
Details for the file rwkv_emb-0.0.1-py3-none-any.whl.
File metadata
- Download URL: rwkv_emb-0.0.1-py3-none-any.whl
- Upload date:
- Size: 392.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6c9530cb826a100365538c5dc132ebb52dbd9de0d1ae10a780f0a9562bce205d
|
|
| MD5 |
47c03f61f3486880e3a82f5c1d1431e1
|
|
| BLAKE2b-256 |
bc758d774a8a69502f63c0c89cbab9a635626ac7873c2d5a7c6cb8f933b07c40
|