PaLM

PaLM copied to clipboard

Will instruction fine tuned models be made available as well

8

Will instruction fine tuned models be made available as well for this

allthingssecurity

``` >>> import torch >>> model = torch.hub.load("conceptofmind/PaLM", "palm_410m_8k_v0") /Users/sebastianperalta/simply/dev/PaLM/venv/lib/python3.11/site-packages/torch/hub.py:294: UserWarning: You are about to download and run code from an untrusted repository. In a future release, this won't be...

sebbyjp

jayyoung0802

Update build_dataset.py

1

actually use the args, also added data_dir arg and added set_seed

tmabraham

Inference on CPU or MPS(Arm based Mac) ?

4

Is there any workaround for running inference on CPU or my arm based Mac M1. Currently trying to run on Mac m1 and I am getting the following error ```...

Pawandeep-prog

I would like to finetune this model for a specific task. Is there finetuning script available for this model?

siddharth0112358

RuntimeError: No available kernel. Aborting execution.

1

When I run the inference logic using the following script, I get `RuntimeError: No available kernel. Aborting execution.` error: ``` A100 GPU detected, using flash attention if input tensor is...

zarandioon

how to train the model,can you explain more detail

2

i want to train my model，can you guide me?

qiuqingpo

Was the BoS/EoS token used during pretraining?

1

The readme suggests use of [GPT-neox-20b tokenizer](https://huggingface.co/EleutherAI/gpt-neox-20b/blob/main/config.json). This tokenizer has a BoS and EoS token mapped to token id 0. However when I look at the model implementation in PaLM-rlhf-pytorch,...

grantdelozier

Training with Hidet compiler

1

Hello! I was wondering if there was anything extra that needed to be done to get training with Hidet compiler working. Out of the box I seem to be running...

RameshArvind