-
-
There's very much a question of whether this is worth the leap for us in the short term, but either way it's worth documenting what this might involve.
First of all, we use scikit-learn for running…
-
So,I was doing some brush up on RL and uptil now what I have seen is that most Deep RLs like actor-critic/DDPG prefer to use MLP/fully connected layers.Now recently I came across the openai request fo…
-
From the result I can see that the result without distillation has artifacts. However I don't understand why.
Did you dig into the w/o distillation model to see where the artifacts come from?
Is it …
-
Dear author,
I've found that in your code, the policy is estimated by a conv1d over the memory followed by a linear transformation, which is different from the recursive formulations in the …
-
Facing the following error when running txt2img on Ubuntu:
`python scripts/stable_txt2img.py --ddim_eta 0.0 --n_samples 8 --n_iter 1 --scale 10.0 --ddim_steps 50 --ckpt sd-v1-4-full-ema.ckpt --promp…
-
I think it would be a good idea to clean up the notebooks in `demo_notebooks` a little bit, especially because we are planning to include them on the website. A few suggestions:
- [ ] Removing the …
-
I get this error when i run the main.py file
Parameters : --base configs/stable-diffusion/v1-inference.yaml --train --gpus=1
I want to train model
`
Global seed set to 23
Running on GPUs 1
Lat…
-
Lora+base is working good
![image](https://github.com/mbzuai-oryx/LLaVA-pp/assets/15274284/7d12…
-
Hi @PanQiWei,
Firstly, thanks for building this repo.
I was wondering if your repo supports modular quantization. For example, the Llama architecture looks like the following:
```
LlamaForCa…