-
In this issue, it is said that related code would be released at https://github.com/RLHF-V/RLAIF-V/issues/6, but I find this [link](https://github.com/RLHF-V/RLAIF-V#data-generation) is empty. Where c…
-
Hi, can you provide the steps, settings and dataset that can be used to replicate the results of Lotto method given in Table 3 and 4? Is the instruction following dataset among `https://huggingface.c…
-
Hello, Ashwinee Panda
I was very impressed with your work and wanted to thank you for the excellent contribution. I am currently following the tutorial using the openbookqa task to finally experime…
-
A significant achievement in aligning Vision-Language Models!
While running the code 'RLAIF-V/muffin/train/train_llava15.py', I noticed that all model parameters are trainable. Due to hardware limi…
-
{
"id": "000000245946",
"image": "000000245946.jpg",
"conversations": [
{
"from": "human",
"value": "\nWhat considerations…
-
### Required prerequisites
- [X] I have read the documentation .
- [X] I have searched the [Issue Tracker](https://github.com/PKU-Alignment/align-anything/issues) and [Discussions](https://github.com…
-
- [ ] Why the author only compare RLAIF with RLHF on task of summarization?
- [ ] How are the performances for other tasks?
- [ ] For 4.1 Datasets, what other ways OpenAI use to filter the data?
- …
-
Hi, there~
After reading the parquets files of the RLAIF-V-Dataset downloaded from Hugging Face, I actually got 83k samples, which is significantly more than the "30k data" mentioned in the README…
-
![img_v3_02do_b346611a-ead2-4f84-9dd9-2b74cdc77afg](https://github.com/user-attachments/assets/68cee71a-4563-4597-b27b-4a26b3552c19)
-
Error: TypeError: LlavaProcessor.__call__() got an unexpected keyword argument 'add_special_tokens'. When trying to run https://github.com/huggingface/trl/blob/main/examples/scripts/dpo_visual.py with…