Jiahao Huo comments

Results 5 comments of


                                            Jiahao Huo

Language distribution of ShareGPT 70K conversation dataset for FastChat T5

> What are all the languages present in the ShareGPT 70,000 conversation dataset which was used to fine-tune FastChat-T5? > > The ReadMe file points to [`data_cleaning.md`](https://github.com/lm-sys/FastChat/blob/main/docs/commands/data_cleaning.md) which was used...

ValueError: Trying to set a tensor of shape torch.Size([128257, 4096]) in "weight" (which has shape torch.Size([128256, 4096])), this look incorrect.

Getting same error in `Llama3.2-vision` after LoRA fine-tuning. I think current Llama models may lack some necessary compatibility for hf features like `accelerate` and `peft` ......

basic_example.py link missing

Hi @bayesways @shirinyamani @burtenshaw , I'm seeking for a simplest way to implement grpo from scratch, but I can't find the complete version of basic_example.py. Any help will be appreciated!!!

Missing Locomo10 Dataset

Same issue. I found a possible file in this [url](https://github.com/snap-research/locomo/blob/main/data/locomo10.json), but nothing for `locomo10_rag.json`.

Missing Locomo10 Dataset

Hi @prateekchhikara thanks for the reply! I also find that running `make run-openai` needs some files named `memories/{idx}.txt`, which haven't been included in the repo as well. Could you further...