The RWKV Language Model
https://github.com/BlinkDL/ChatRWKV
https://github.com/BlinkDL/RWKV-LM
```python
# set these before import RWKV
os.environ['RWKV_JIT_ON'] = '1'
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 (!!! DOES NOT support CPU !!!)
# fp32 = good for CPU
# bf16 = worse accuracy, 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='/fsx/BlinkDL/HF-MODEL/rwkv-4-pile-169m/RWKV-4-Pile-169M-20220807-8023', strategy='cpu fp32')
pipeline = PIPELINE(model, "20B_tokenizer.json") # 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 = [0], # 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')
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')
```
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
【资源说明】 基于RWKV大模型RWKV World模型数据集植物花卉数据集[PlantFlower Datasets 【备注】 1、该项目是个人高分项目源码,已获导师指导认可通过,答辩评审分达到95分 2、该资源内项目代码都经过测试运行成功,功能ok的情况下才上传的,请放心下载使用! 3、本项目适合计算机相关专业(如软件工程、计科、人工智能、通信工程、自动化、电子信息等)的在校学生、老师或者企业员工下载使用,也可作为毕业设计、课程设计、作业、项目初期立项演示等,当然也适合小白学习进阶。 4、如果基础还行,可以在此代码基础上进行修改,以实现其他功能,也可直接用于毕设、课设、作业等。 欢迎下载,沟通交流,互相学习,共同进步!
资源推荐
资源详情
资源评论
收起资源包目录
基于RWKV大模型RWKV World模型数据集植物花卉数据集[PlantFlower Datasets]源码+详细说明+全部数据资料 高分项目.zip (26个子文件)
PlantFlowerDatasets-main
data
PlantFlower_text_document.bin 8.3MB
plantflower_cnflora_data_text_document.bin 70.81MB
plantflower_cnflora_data_text_document.idx 704KB
PlantFlower_text_document.idx 100KB
cnflora_data_text_document.bin 62.21MB
cnflora_data_text_document.idx 604KB
LICENSE 1KB
pic20230621195113.png 113KB
pic20230706105642.png 193KB
RWKV-LM-LoRA[World模型]训练文件
RWKV-v4neo
src
rwkv_vocab_v20230424.txt 1.04MB
utils_word.py 5KB
rwkv_tokenizer.py 3KB
chat_word.py 19KB
rwkv_pip_package
src
rwkv
utils.py 5KB
__init__.py 0B
rwkv_vocab_v20230424.txt 1.04MB
model.py 32KB
cuda
wrapper.cpp 5KB
operators.cu 8KB
rwkv_tokenizer.py 3KB
LICENSE 11KB
pyproject.toml 499B
MANIFEST.in 47B
README.md 4KB
README.md 4KB
171265889347208773632.zip 416B
共 26 条
- 1
资源评论
不走小道
- 粉丝: 3221
- 资源: 5113
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 单家独院式农房户型设计110平-t3.dwg
- 有了DevExpress VCL 23.2.6 Full Source 这个版本源码,怎么能没有相应的Demo呢
- GIN+SCUI企业级后台管理系统;后端基于go语言开发,前端基于vue3开发的scui框架
- 单家独院式图纸110平方米户型水电图.dwg
- aardio - 阿里云mqtt实例
- 基于python后端开发框架
- seata-server 1.4.0和2.0.0
- signal-and-system信号与系统
- career.it.signals-systems信号与系统
- 基于TCP-IP实现的斗地主游戏(ARM-LINUX)C源码-95分以上课程设计
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功