transformerlab-app

transformerlab-app copied to clipboard

mlx-community/Mixtral-8x7B-Instruct-v0.1-hf-4bit-mlx does not generate tokens

3

daboe01

Hello, I really freaking love the app and the interface, it would be really cool in llamafile is added as a supporting inference engine. The good folks at Mozilla.ai have...

aditya-y47

Local Connection installer: No error reported if there are exceptions during "Install Dependencies" step

1

If flash_attn fails to build using the UI installer, the app will just report Success and continue. Then you'll just hit weird errors in the app later on. It would...

dadmobile

MacOS-X using mlx - Missing parameters: lm_head.biases lm_head.scales.

1

Getting this error running a local fine-tune using mlx. Unclear where to set these parameters ``` Training beginning: Adaptor will be saved as: /Users/pnayak/.transformerlab/workspace/plugins/mlx_lora_trainer/my-adaptor-1.npz Writing logs to: /Users/pnayak/.transformerlab/workspace/tensorboards/job5/20240404-181024 Loading pretrained...

prashantnayak-edu

Generate config.json files for exported models

1

We need information in this file for RAG. Look to see if mlx-lm conversion does this now?

dadmobile

Control where models and other large data is stored

2

1. You can set HF_HOME, or just HF_HUB_CACHE and TransformerLab will respect this. Should you be able to change this through TransformerLab? You can also set where specific models download....

dadmobile

install script requires curl but doesn't check for it

1

When running the install script, we should check that curl exists and alert user if not

aliasaria

Tracking issue for: - [ ] https://github.com/transformerlab/transformerlab-app/security/code-scanning/2

aliasaria

If there is a crash, the whole window goes blank. Is there a way we can detect the crash? https://www.electronjs.org/docs/latest/api/web-contents#event-crashed and either show an error screen or restart? https://stackoverflow.com/questions/45919195/electron-recovery-after-crash-on-render-process

aliasaria

al-sadr and dadmobile both got: > ImportError: Using `load_in_8bit=True` requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes `pip install -i https://test.pypi.org/simple/ bitsandbytes` or pip install bitsandbytes` Can...

dadmobile