-
On my x86 MBP(not M1/M2), with eGPU[rx6800 16G], it can load model(see #65), but when calculate the 1st token, it gets a very big number and return error.
using `mps fp32`
error log:
```
(Ch…
-
When you updated the package rwkv 0.7.3 i started to get the following error that I m not able to fix when running the chat.py of V2
^C
CondaError: KeyboardInterrupt
(pytorch_p39) ubuntu@ip-17…
-
I am not sure what happenning here, looks like tokenizer problem
as you can see https://github.com/saharNooby/rwkv.cpp/blob/1c363e6d5f4ec7817ceffeeb17bd972b1ce9d9d0/rwkv/chat_with_bot.py#LL169C18-L…
-
# 每日安全资讯（2023-08-15）
- HackerOne Hacker Activity
- [ ] [HTML injection on newsroom.snap.com/* via search?q=1](https://hackerone.com/reports/2018615)
- [ ] [Path traversal allows tricking the Talk…
-
Hello, I've downloaded a recent RWKV-4-World model from Huggingface. The code runs. However the output is nonsense.
```
from rwkv.model import RWKV
from rwkv.utils import PIPELINE, PIPELINE_ARGS
…
-
Switched over to Linux, installed ninja, and have a compile issue perhaps.
Suggestions?
```
python chat.py
ChatRWKV v2 https://github.com/BlinkDL/ChatRWKV
English - cuda fp16 - /media/mai…
-
I'm seeing different versions of RWKV, what is the system requirements in terms of of VRAM and RAM? Does the readme have this information?
-
Hi do you have any examples of where it is conversational? I am trying to find the best way to send conversational history.
Right now, the answer is too long.
:
File "C:\Users\yongy\chatrwkv\v2\chat.py", line 125, in
pipeline = PIPELINE(model, f"{current_path}/2…
-
```
(base) ✘-1 desktop:~/dev/projects/ai/ChatRWKV [main|✚ 2]> RWKV_CUDA_ON=1 python convert_model.py --strategy 'cuda fp16i8 *10+' --out ~/data/ai/models/RWKV/RWKV-4-Raven-14B-v8-EngAndMore-20230408-…