-
Hi all - please chime in with any and all feedback to help drive the direction of glTF beyond 2.0. Even simple +1/-1's for topics are appreciated.
How much should we focus on building out the soft…
-
目前在```src/llmtuner/tuner/rm/trainer.py```中```compute_loss```这一部分采用的loss计算是源自InstructGPT中的提出的 $Loss=-log(\sigma (r_{\theta }(x,y_c)-r_{\theta }(x, y_r)))$ 。但在LLaMA2的论文中提到了可以在loss中添加一个m项的方式标定不同的偏好差别，原文如…
-
### System Info
- `transformers` version: 4.35.0
- Platform: Linux-5.16.19-76051619-generic-x86_64-with-glibc2.35
- Python version: 3.10.11
- Huggingface_hub version: 0.17.3
- Safetensors versi…
-
微博内容精选
-
as the title states.
please only use this thread for questions and discussion and open new feature requests for actual issues with OpenCNCPilot.
Martin
-
Took a crack at what I think this thing should do (with ChatGPT of course).
## Ideal Scope and Capabilities
### 1. Task Understanding
- **Natural Language Processing (NLP)**: The AI must exc…
-
I've just run into an odd issue with FSDP & RewardTrainer. It seems then when using FSDP, the output of the (sequence classification) model's `forward` function isn't as expected.
Normally, it retur…
-
Hello ,I get an error at reward_modeling(adapter_model) marge base model.
error message:
File "/home/airuser/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2152, in load…
-
Q1) any minimum requirement for running h2ogpt docker ?
should GPU have at least N GB ?
- got " torch.cuda.OutOfMemoryError: CUDA out of memory."
- at now , using GeForce RTX…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
训练脚本：
--stage ppo \
--do_train \
--cutoff_len 1024 \
--template default \
--model_n…