-
Very nice work!
I'm runing PPO using the hhrlhf datasets in verl repo. And the error is here.
```
File "/home/syx/rlhf/verl/single_controller/ray/base.py", line 395, in func
return getattr…
-
### Description
When running the `examples/ppo_trainer/run_deepseek_megatron.sh` script with the base model `deepseek-llm-7b-chat`, I encountered an unexpected behavior related to the `num_hidden_lay…
-
### Priority
P1-Stopper
### OS type
Ubuntu
### Hardware type
Xeon-other (Please let us know in description)
### Installation method
- [ ] Pull docker images from hub.docker.com
- [X] Build dock…
-
I'm using a Mistral model and want to only train on responses. `train_on_responses_only` is supposed to only mask the user prompt, however, the following code masks **both** the user and assistant mes…
-
### System Info
Transformers Patch release v4.45.2
PyTorch 1.10.1
Python 3.8.0
cuda 11.1
NVIDIA V100
### Who can help?
@gante @zucchini-nlp @Rocketknight1
### Information
- [ ] The official …
-
Obsidian and all plugins up-to-date
Smart Connect App cannot finish the embedding.
Reloading, re-installing Smart Connect app and Smart-Connections plugin -> no result
I have attached the errors …
-
我用本地下载好的模型权重和本地数据进行sft的时候，这样启动，但是报模型没注册，现在还不支持加载本地的模型权重吗？
export NPROC_PER_NODE=8 \
export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
export HCCL_SOME_VARIABLE=value \
export OMP_NUM_THREADS=192
…
-
**This is different than the batchAPI**, this still sends requests to the /chat/completions API but sends a list of prompts in each request.
Since we are hitting request limits instead of token li…
-
I have a complex input file of semi structured data that I want to re-structure using instructor. It does a great job with the direct chat completion calls, returning my Parsed Pydantic model just fin…
-
### Confirm this is a feature request for the .NET library and not the underlying OpenAI API
- [X] This is a feature request for the .NET library
### Describe the feature or improvement you are requ…