The RWKV Language Model
Project description
The RWKV Language Model
https://github.com/BlinkDL/RWKV-LM
https://github.com/BlinkDL/ChatRWKV
# !!! set these before import RWKV !!!
# os.environ["RWKV_V7_ON"] = '1' # ==> enable RWKV-7 mode
os.environ['RWKV_JIT_ON'] = '1' # '1' for better speed
os.environ["RWKV_CUDA_ON"] = '0' # '1' to compile CUDA kernel (10x faster), requires c++ compiler & cuda libraries
########################################################################################################
#
# Use '/' in model path, instead of '\'. Use ctx4096 models if you need long ctx.
#
# fp16 = good for GPU
# fp32 = good for CPU
# bf16 = supports CPU
# xxxi8 (example: fp16i8, fp32i8) = xxx with int8 quantization to save 50% VRAM/RAM, slower, slightly less accuracy
#
# We consider [ln_out+head] to be an extra layer, so L12-D768 (169M) has "13" layers, L24-D2048 (1.5B) has "25" layers, etc.
# Strategy Examples: (device = cpu/cuda/cuda:0/cuda:1/...)
# 'cpu fp32' = all layers cpu fp32
# 'cuda fp16' = all layers cuda fp16
# 'cuda fp16i8' = all layers cuda fp16 with int8 quantization
# 'cuda fp16i8 *10 -> cpu fp32' = first 10 layers cuda fp16i8, then cpu fp32 (increase 10 for better speed)
# 'cuda:0 fp16 *10 -> cuda:1 fp16 *8 -> cpu fp32' = first 10 layers cuda:0 fp16, then 8 layers cuda:1 fp16, then cpu fp32
#
# Basic Strategy Guide: (fp16i8 works for any GPU)
# 100% VRAM = 'cuda fp16' # all layers cuda fp16
# 98% VRAM = 'cuda fp16i8 *1 -> cuda fp16' # first 1 layer cuda fp16i8, then cuda fp16
# 96% VRAM = 'cuda fp16i8 *2 -> cuda fp16' # first 2 layers cuda fp16i8, then cuda fp16
# 94% VRAM = 'cuda fp16i8 *3 -> cuda fp16' # first 3 layers cuda fp16i8, then cuda fp16
# ...
# 50% VRAM = 'cuda fp16i8' # all layers cuda fp16i8
# 48% VRAM = 'cuda fp16i8 -> cpu fp32 *1' # most layers cuda fp16i8, last 1 layer cpu fp32
# 46% VRAM = 'cuda fp16i8 -> cpu fp32 *2' # most layers cuda fp16i8, last 2 layers cpu fp32
# 44% VRAM = 'cuda fp16i8 -> cpu fp32 *3' # most layers cuda fp16i8, last 3 layers cpu fp32
# ...
# 0% VRAM = 'cpu fp32' # all layers cpu fp32
#
# Use '+' for STREAM mode, which can save VRAM too, and it is sometimes faster
# 'cuda fp16i8 *10+' = first 10 layers cuda fp16i8, then fp16i8 stream the rest to it (increase 10 for better speed)
#
# Extreme STREAM: 3G VRAM is enough to run RWKV 14B (slow. will be faster in future)
# 'cuda fp16i8 *0+ -> cpu fp32 *1' = stream all layers cuda fp16i8, last 1 layer [ln_out+head] cpu fp32
#
# ########################################################################################################
from rwkv.model import RWKV
from rwkv.utils import PIPELINE, PIPELINE_ARGS
# download models: https://huggingface.co/BlinkDL
model = RWKV(model='RWKV-x060-World-1B6-v2.1-20240328-ctx4096', strategy='cpu fp32')
pipeline = PIPELINE(model, "rwkv_vocab_v20230424") # for "world" models
# pipeline = PIPELINE(model, "20B_tokenizer.json") # for "pile" models, 20B_tokenizer.json is in https://github.com/BlinkDL/ChatRWKV
ctx = "\nIn a shocking finding, scientist discovered a herd of dragons living in a remote, previously unexplored valley, in Tibet. Even more surprising to the researchers was the fact that the dragons spoke perfect Chinese."
print(ctx, end='')
def my_print(s):
print(s, end='', flush=True)
# For alpha_frequency and alpha_presence, see "Frequency and presence penalties":
# https://platform.openai.com/docs/api-reference/parameter-details
args = PIPELINE_ARGS(temperature = 1.0, top_p = 0.7, top_k = 100, # top_k = 0 then ignore
alpha_frequency = 0.25,
alpha_presence = 0.25,
alpha_decay = 0.996, # gradually decay the penalty
token_ban = [], # ban the generation of some tokens
token_stop = [], # stop generation whenever you see any token here
chunk_len = 256) # split input into chunks to save VRAM (shorter -> slower)
pipeline.generate(ctx, token_count=200, args=args, callback=my_print)
print('\n')
# !!! model.forward(tokens, state) will modify state in-place !!!
out, state = model.forward([187, 510, 1563, 310, 247], None)
print(out.detach().cpu().numpy()) # get logits
out, state = model.forward([187, 510], None)
out, state = model.forward([1563], state) # RNN has state (use deepcopy to clone states)
out, state = model.forward([310, 247], state)
print(out.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-0.8.28.tar.gz
(407.9 kB
view details)
Built Distribution
rwkv-0.8.28-py3-none-any.whl
(410.0 kB
view details)
File details
Details for the file rwkv-0.8.28.tar.gz
.
File metadata
- Download URL: rwkv-0.8.28.tar.gz
- Upload date:
- Size: 407.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.10.13
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 62dab7afe791c0377b936dcd229fdd10319de714ac5e514ba8db3d23c14295a8 |
|
MD5 | 1d3778fc389859b42c1b390fcce879f7 |
|
BLAKE2b-256 | d1829995003bd7f93e1e6433b6ce8fa21a1079fcd35095a9cb7d8c0439f884c1 |
File details
Details for the file rwkv-0.8.28-py3-none-any.whl
.
File metadata
- Download URL: rwkv-0.8.28-py3-none-any.whl
- Upload date:
- Size: 410.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.10.13
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 459ead27e6d68f72de935b7ede876b0820fae95a6fbf77c434c05d4b29304e40 |
|
MD5 | fd55679c0649c10227746e3891e6c25c |
|
BLAKE2b-256 | b25fbcc13f66cc4f849000d68c11ffa7e85e05f9a552a5eba6c3c0326f201eb8 |