Skip to content
New issue

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

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

Already on GitHub? Sign in to your account

Add requirements for each model size #20

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,19 @@ RWKV is a RNN with Transformer-level LLM performance, which can also be directly

So it's combining the best of RNN and transformer - **great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding** (using the final hidden state).

**Download RWKV-4 0.1/0.4/1.5/3/7/14B weights**: https://huggingface.co/BlinkDL
**Download RWKV-4 0.1/0.4/1.5/3/7/14B weights**: https://huggingface.co/BlinkDL

Requirements: (rough estimate is disk size = vram size = 2 x parameters)
| Model Parameters | Size in disk & VRAM |
|--------------------------------------------------------------|--------------------------|
| [RWKV-169m](https://huggingface.co/BlinkDL/rwkv-4-pile-169m) | 339 MB |
| [RWKV-430m](https://huggingface.co/BlinkDL/rwkv-4-pile-430m) | 861 MB |
| [RWKV-4-1b5](https://huggingface.co/BlinkDL/rwkv-4-pile-1b5) | 3.03 GB |
| [RWKV-4-3b](https://huggingface.co/BlinkDL/rwkv-4-pile-3b) | 5.97 GB |
| [RWKV-4-7b](https://huggingface.co/BlinkDL/rwkv-4-pile-7b) | 14.8 GB |
| [RWKV-4-14b](https://huggingface.co/BlinkDL/rwkv-4-pile-14b) | 28.3 GB |



**RWKV chatbot**: https://github.com/BlinkDL/ChatRWKV

Expand Down