-
### Description of the new feature / enhancement
When Awake is started via the CLI, it shows a log screen with the options that have been used to start it, and this dialog remains on screen:
Hi,
I've been attempting to reproduce an experiment involving the finetuning of the Llama-2-7b-hf model,…
-
When training the llm model according to the example, the following error occurred
Qwen1.5-0.5B-Chat and chatglm3-6b had same error.
Please help me check where the problem is.
Thanks !!!
…
-
**Describe the bug**
Following the tutorial from the MS Documentation on how to use Graph Toolkit with Teams Tab applications. After authorizing the app, the code throws errors in the console a…
-
Scanflow described ML workflows need to be deployed on K8s clusters. In order to improve the performance of each workflow job or service, this issue requests Scanflow could use default scheduler or en…
-
We're using hyper-rustls with the `webpki-tokio` feature enabled. The intention behind this is that we vendor the CA via webpki and make this explicitly extensible with custom CAs in the future.
Ru…
-
你好，我按照脚本里默认的超参数（learning rate），以及论文提到各参数配置、偏好数据，在ALMA-7B-Lora上做CPO，但是训出来的模型输出大量重复前文甚至不翻译的情况，如下图（zh->en,raw_res 是没用utils里的clean函数的结果），请问是哪里没设好超参吗？谢谢你。
```
#!/bin/bash
#SB…
-
I appreciate your great work in zero123.
I want to retrain zero123 on medical data. My dataset contains about 700 samples, using the same data processing method as in the paper. Each sample has 12 …
ys830 updated
1 month ago