niansa/tuxifan comments

Results 303 comments of


                                            niansa/tuxifan

macOS 10.13.6 (High Sierra): dyld: cannot load 'gpt4all-lora-quantized-OSX-intel'

Stale, please open a new issue if this still occurs

Whats the max amount of input text that can be supplied ?

Stale, please open a new issue if this is still relevant.

The response sometimes includes "### Instruction: and ### Response:"

stale, and should be fixed by now

Chat just exits after few exchanges.

Stale, please open a new issue if this still occurs

Secret Unfiltered Checkpoint still refuses to answear some questions.

Stale, please open a new issue if this still occurs

Got stuck in response loop

stale

Download weights from huggingface to help us save bandwith

I guess uploading to other sources may be an option too :smile: Unfortunately most people don't have servers with a connection beefy enough to support this.

Reducing the time needed to reload a piece of text into the model by caching the state

> #174 also asked this, or do you have something else in mind? Basically yes, except that interactive user input and generated results should be saved too. So basically you...

Is this the 4bit version?

It's the original fb version.

High performance API

> You have RESTful APIs for all the large LLM providers like OpenAI. You send your inputs and generation params, the service sends you back the generated response string. Sure...