Rwkv Raven 14b

🚀 RWKV-4 | 14B参数聊天版本（Raven）模型卡片

RWKV是由Bo Peng领导的项目。您可以在Johan Wind的博客文章此处和此处了解更多关于模型架构的信息。您还可以加入RWKV Discord服务器来深入了解该项目。

📚 目录

0. 简要说明
1. 模型详情
2. 使用方法
3. 引用信息

TL;DR

以下是来自原始仓库的描述：

RWKV是一种具有Transformer级大型语言模型性能的循环神经网络（RNN）。它可以像GPT一样直接进行训练（可并行化）。它结合了RNN和Transformer的优点——性能出色、推理速度快、节省显存、训练速度快、具有“无限”上下文长度，并且能免费获取句子嵌入。

✨ 主要特性

模型详情

模型架构的详细信息可在上述博客文章以及Hugging Face关于集成的博客文章中找到。

📦 安装指南

将原始权重转换为Hugging Face格式

您可以使用convert_rwkv_checkpoint_to_hf.py脚本，通过指定原始权重的仓库ID、文件名和输出目录来进行转换。您还可以选择通过传递--push_to_hub标志和--model_name参数，将转换后的模型直接推送到Hugging Face Hub，以指定推送转换后权重的位置。

python convert_rwkv_checkpoint_to_hf.py --repo_id RAW_HUB_REPO --checkpoint_file RAW_FILE --output_dir OUTPUT_DIR --push_to_hub --model_name dummy_user/converted-rwkv

💻 使用示例

生成文本

您可以使用AutoModelForCausalLM和AutoTokenizer类从模型生成文本。展开以下部分，了解如何在不同场景下运行模型： “Raven”模型需要以特定方式进行提示，您可以在集成博客文章中了解更多相关信息。

基础用法

在CPU上运行模型

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("RWKV/rwkv-raven-14b")
tokenizer = AutoTokenizer.from_pretrained("RWKV/rwkv-raven-14b")

prompt = "\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."

inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(inputs["input_ids"], max_new_tokens=40)
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))

高级用法

在单个GPU上运行模型

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("RWKV/rwkv-raven-14b").to(0)
tokenizer = AutoTokenizer.from_pretrained("RWKV/rwkv-raven-14b")

prompt = "\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."

inputs = tokenizer(prompt, return_tensors="pt").to(0)
output = model.generate(inputs["input_ids"], max_new_tokens=40)
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))

在GPU上以半精度运行模型

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("RWKV/rwkv-raven-14b", torch_dtype=torch.float16).to(0)
tokenizer = AutoTokenizer.from_pretrained("RWKV/rwkv-raven-14b")

prompt = "\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."

inputs = tokenizer(prompt, return_tensors="pt").to(0)
output = model.generate(inputs["input_ids"], max_new_tokens=40)
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))

在多个GPU上运行模型

# pip install accelerate
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("RWKV/rwkv-raven-14b", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("RWKV/rwkv-raven-14b")

prompt = "\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."

inputs = tokenizer(prompt, return_tensors="pt").to(0)
output = model.generate(inputs["input_ids"], max_new_tokens=40)
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))

📄 许可证

引用信息

如果您使用此模型，请考虑引用原始工作，原始仓库位于此处。

数据集信息