Skip to content

Adds instructions and works on linux as well #9

New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Merged
merged 5 commits into from
Apr 3, 2023

Conversation

hypnopump
Copy link
Member

This updates instructions and works on linux as well. Still couldnt get it to work on Mac M1 due to arm vs x86 mismatch.

@hypnopump hypnopump marked this pull request as ready for review April 2, 2023 22:54
README.md Outdated
@@ -31,20 +31,25 @@ cmake --build . --config Release

If everything went OK, `bin\Release\rwkv.dll` file should appear.

### 2. Download an RWKV model from [Hugging Face](https://huggingface.co/BlinkDL) and convert it into `ggml` format

### 2. Download an RWKV model from [Hugging Face](https://huggingface.co/BlinkDL) like [this one](https://huggingface.co/BlinkDL/rwkv-4-pile-169m/blob/main/RWKV-4b-Pile-171M-20230202-7922.pth) and convert it into `ggml` format
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As RWKV author says,

Use RWKV-4 models (NOT RWKV-4a, NOT RWKV-4b) unless you know what you are doing.

4a and 4b models are experiments containing new model parts, and will not work good with rwkv.cpp. Please change links and file names below to use regular 4 model, not 4b :)

README.md Outdated
@@ -75,9 +88,13 @@ Example of using `rwkv.cpp` in your custom Python script:
import rwkv_cpp_model
import rwkv_cpp_shared_library

# change by model paths used above (quantized or full weights)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
# change by model paths used above (quantized or full weights)
# Change to model paths used above (quantized or full weights)

import sys
import argparse
import sampling
import tokenizers
import rwkv_cpp_model
import rwkv_cpp_shared_library
from pathlib import Path
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would prefer to use import pathlib and pathlib.Path below for style consistency

@hypnopump hypnopump requested a review from saharNooby April 3, 2023 06:34
@saharNooby saharNooby merged commit 4f1df7c into RWKV:master Apr 3, 2023
# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants