regstuff

Complied main.exe that can probably be used on Windows 10/11 x64 PCs

2

One of my teammates compiled an exe and it was working quite well on most of our other Windows systems, so I thought I'd share it for those having difficulties...

After successfully installing `Successfully installed InstaLiveCLI-1.0.3` I get a module not found "No module named 'InstaLiveCLI'" when I run the below code ``` from InstaLiveCLI import InstaLiveCLI live = InstaLiveCLI(...

Trying to understand what Random Seed does

1

Could anyone explain what it does? I know about random seed in general, but I don't understand what purpose it could serve in the context of a Whisper user. My...

[bug]: 'Combine' object has no attribute 'set_parse_action'

2

### Is there an existing issue for this? - [X] I have searched the existing issues ### OS Linux ### GPU amd ### VRAM 32 ### What happened? After inputing...

Keeping the model loaded on RAM

6

Is there a way to keep the model loaded in the RAM between successive runs? I have an api like setup, and every time a prompt comes in, the model...

[Feature]: qdrant as a vector store

6

### Is your feature request related to a problem? Please describe. Hi. Glad someone finally made this. Been on my mind for a long time. Any chance of supporting qdrant...

4-bit quantization to reduce VRam requirement

5

Hi, Is it possible to use something like GPTQ to get a 4-bit quantized version of the latest 7B Instruct model. That's got to be one of the fastest and...

gptq 4-bit quantized version

3

Hi, Do you guys have any plans to make a gptq 4-bit quantized version of your models. That would cut VRAM usage and improve inference speed a lot, without much...

Word in proximity search gets highlighted twice, even when not matched

1

**Describe the bug** Consider a sentence such as: something word11 something something something word10 something something something something word10 something Here, word10 appears twice, The two instances of word10 are...

Getting the number of vectors in a bruteforce index

1

Hi Is there any way to get the number of elements currently in a bruteforce index (not the maximum elements). Something similar to get_current_count() that works for bf index also?