transformerlab-app

transformerlab-app copied to clipboard

On a mac, I am finding that every time I download a model it says "Failed To Download" when it finishes downloading. The API is reporting this error: sqlite3.OperationalError: database...

dadmobile

Allow Changing Default Engine Port from 8000

3

I do not know if it is possible to change the port 8000 to another, because this in local at home is used by Portainer? I think it's possible, please...

DaSNyB

Using Gemma 2 9B IT: - on Fastchat it returns "Hello Hello Hello Hello Hello..." - on MLX it returns a correct answer but ends with ""

dadmobile

Because the server is running in WSL, when the application passes a windows style path to look for models the backend isn't able to access. API could detect if it's...

dadmobile

Currently Model Zoo displays models alphabetically. Many users can only install models of a certain size so ability to filter or sort would be helpful.

dadmobile

Running an mlx_server on an imported mlx model fails

1

### Running Transformer Lab v0.4.0 on Macbook Pro M1 1. Imported a quantized model converted from huggingface via: ```sh python -m mlx_lm.convert \ --hf-path mistralai/Mistral-Nemo-Instruct-2407 \ -q ``` 2. In...

jasonnathan

Add 4-bit MLX models of small models

2

Maybe some of TinyLlama, Phi, Qwen2 small models?

dadmobile

For some reason the Llama 3 and Llama 3.1 models can't load in to GPU before some timeout kicks in (2 minutes). I can see that there are 4 shards...

dadmobile

Dataset download button not not set to "Downloaded" after download

4

If you download a dataset it flips to "Downloading" when you are downloading but then when it is done it flips to "Download". Then at a later moment the screen...

dadmobile

aliasaria