-
Command in [RWKV-v4neo](https://github.com/BlinkDL/RWKV-LM/tree/main/RWKV-v4neo)
```
python train.py --load_model /home/user/models/LLM/rwkv/RWKV-5-World-3B-v2-20231118-ctx16k.pth --proj_dir ./tes…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
Traceback (most recent call last):
File "/mlx_devbox/users/xiao.gao/repo/5012/LLaMA-Efficient-Tuning/…
-
Hey there,
Worked on this quite a lot yesterday with the help of GPT-4, but I'm having some issues with errors similar to the following:
```
Traceback (most recent call last):
File "/mnt/c/U…
-
对于只有V100情况下,用S^2 attention做推理,关于group实现是否有问题呢(forward_noflashattn)
```
bsz, q_len, _ = hidden_states.size()
group_size = int(q_len * group_size_ratio)
```
q_len在推理的时候长度等于1,这样的话group_size就会变成0,然…
-
![image](https://user-images.githubusercontent.com/32290891/200547170-b28804d2-949c-4529-b7e6-e9fd7dfd2f0c.png)
While training MipNeRF360 on dataset nerf_360_v2 and it turned out loss nan
Config as…
-
首先,想请教有没有requirement.txt文件。因为之前训练没有问题,后面环境更换了之后按照
# Found torch 1.13.0a0+340c412, recommend 1.13.1+cu117 or newer
# Found deepspeed 0.12.6, recommend 0.7.0 (faster than newer versions)
# Found pyto…
-
[This line for initialization of `dataloader_val` ](https://github.com/slei109/PATNet/blob/1d4c93343e4d18d2b2c8ffa4b3a9665da4dfac23/train.py#L88)
According to my understanding, the script `train.py…
-
I downloaded the llama-2-7b and run the command as they metioned
```
torchrun --nproc_per_node 1 example_text_completion.py \
--ckpt_dir llama-2-7b/ \
--tokenizer_path tokenizer.model \
…
-
Originally posted as part of the following issue:
- https://github.com/oobabooga/text-generation-webui/pull/393#issuecomment-1501036152
As part of that, I got: `ModuleNotFoundError: No module na…
-
Hello,
thank you for the great tool.
Unfortunately I am getting the following error message if I call /api/v1/param/. All other calls seems to work fine.
Call:
pi@htraspi:~ $ curl -X GET "…