Skip to main content

RWKV-4

This page covers how to use the RWKV-4 wrapper within LangChain. It is broken into two parts: installation and setup, and then usage with an example.

Installation and Setup​

  • Install the Python package with pip install rwkv
  • Install the tokenizer Python package with pip install tokenizer
  • Download a RWKV model and place it in your desired directory
  • Download the tokens file

Usage​

RWKV​

To use the RWKV wrapper, you need to provide the path to the pre-trained model file and the tokenizer's configuration.

from langchain_community.llms import RWKV

# Test the model

```python

def generate_prompt(instruction, input=None):
if input:
return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

# Instruction:
{instruction}

# Input:
{input}

# Response:
"""
else:
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.

# Instruction:
{instruction}

# Response:
"""


model = RWKV(model="./models/RWKV-4-Raven-3B-v7-Eng-20230404-ctx4096.pth", strategy="cpu fp32", tokens_path="./rwkv/20B_tokenizer.json")
response = model.invoke(generate_prompt("Once upon a time, "))

API Reference:

Model File​

You can find links to model file downloads at the RWKV-4-Raven repository.

RWKV VRAM
Model | 8bit | bf16/fp16 | fp32
14B | 16GB | 28GB | >50GB
7B | 8GB | 14GB | 28GB
3B | 2.8GB| 6GB | 12GB
1b5 | 1.3GB| 3GB | 6GB

See the rwkv pip page for more information about strategies, including streaming and cuda support.


Help us out by providing feedback on this documentation page: