-
**Describe the bug**
Running ns-train gaussian-splatting crashed with assertion failure
**To Reproduce**
I built a docker image using the gaussian-splatting branch.
1. `git clone https://githu…
-
### Describe the bug
After updating OpenLLM from 0.1.20 to 0.2.0, I tried to load Baichuan-13B-Chat model as following:
```
openllm start baichuan --model-id /home/user/.cache/modelscope/hub/baic…
-
我在使用`pipeline parallelism`对`Moss-7B`底座模型进行`superivised finetuning`，实验环境为`4xV100`，但是我发现在训练过程中，loss一直都是nan，请问可能是什么原因？
我的配置如下：
```
"""
使用CoLLie微调Moss-base模型
"""
import sys
sys.path.append('..')
…
-
## Description
The ppo script hangs when logging to wandb in a multi-gpu setup. But, it works fine without wandb.
## Potential diagnosis
It is caused when calling `log_stats` in [here](http…
-
Hi there,
I'm trying to experiment with "RL while learning Minmax penalty" ([paper](https://arxiv.org/abs/2306.00035), [code](https://github.com/geraudnt/rosarl/blob/main/learning_minmax_penalty.py…
-
Quoting the ARL contract (see also draft_sayma_metlino_procurement_20160805.pdf):
* [ ] f,p,a,u modulation by RTIO (eDRTIO) for all interpolators
* [ ] Coherent phase mode (implemented in kernel API…
-
**I want to implement and contribute the following feature to matRad:**
The [TROTS dataset](https://sebastiaanbreedveld.nl/trots/) is a very interesting set of CTs and treatment plans for benchmarkin…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
CUDA_VISIBLE_DEVICES=0 python3.10 train_bash.py \
--stage sft \
--model_name_or_path ../model/…
-
Initial weights:
```rust
[
0.4, 0.6, 2.4, 5.8, // initial stability
4.93, 0.94, 0.86, 0.01, // difficulty
1.49, 0.14, 0.94, // success
…
-
https://research.fb.com/facebook-open-sources-elf-opengo/
ELF OpenGo
ELF OpenGo is a reimplementation of AlphaGoZero / AlphaZero. It was trained on 2,000 GPUs over a two week period, and has achie…