Bedir Tapkan

Using ManyToMany connections for inlines

4

Is there any way to use ManytoMany model relations to create inline connected forms? I did achieve using the foreign key but didn't find anything about ManytoMany, if it is...

Cmake version requirements

1

I get this error with CMake 3.16.3 > CMake 3.17 or higher is required. You are running version 3.16.3 In the installation guide, it still says 3.12 https://github.com/deepmind/open_spiel/blob/ae9371a1c92a6bfb2312e8315882bfe7d3e69a1a/docs/install.md?plain=1#L28

Hey, First of all thanks for the video, post, and the code. I really find it underrated as I went over almost every single resource on AZ. I am still...

vRAM usage display for 70B models

3

I love how detailed the 7-8B models are displayed with their expected VRAM usage on the readme + docs. I would love to see 70B as well, I think it...

Context Length Increse Results in OOM

2

I am testing TorchTune with some settings I trained my models on. My go-to single-device library was unsloth, as it provides great memory and time savings. Based on my Llama...

File issues with 70B Lora setup

3

The 70B Lora setup is specifying checkpoints in the default config. But when I download the model it only has the `original/consolidated.0*.pth` files. When I try to run the model...

Why is Chapter 11 excluded?

2

Hi, I can't really see why is chapter 11, function approximation with off-policy methods are excluded in the function approximation chapter? It is essential, plus the exercises basically are in...

Hi! This is a well-developed tool, yet it is lacking good documentation, a bit more detailed documentation might have helped people better. (plus it will be a better representation)

Using Collapse

4

Hi, I am trying to use the collapse shortcode, but I couldn't figure out how. I am really new to Hugo so I struggle adding new stuff. I was able...

Having issues on Running Llama-3-70B

1

Hi, I am trying to run fine-tuning Llama-3-70B-Instruct on Sagemaker Notebook with `p4de.24xlarge` instance. I am not sure whats wrong, but it seems like package cannot see `torchtune.models.llama3.lora_llama3_70b` module. The...