localGPT

localGPT copied to clipboard

Hi, I have 2 issues with vicuna 7B model - uncensored 1) I ask questions in other language (not English), that generally works ok with the model. I have proper...

MocMilo

ImportError: cannot import name 'UnstructuredExcelLoader' from 'langchain.document_loaders'

2

I had things working but after I pulled the new code this morning, when I run imgest.py I get a "ImportError: cannot import name 'UnstructuredExcelLoader' from 'langchain.document_loaders'" message.

johnkmayo

Now u can choose model by number, or by its full-name.

3

`python run_localGPT.py` `I choose:` (u input: ) `3` (loading NousResearch/Nous-Hermes-13b) or (u input: ) `NousResearch/Nous-Hermes-13b` (loading NousResearch/Nous-Hermes-13b) --- 1 TheBloke/vicuna-7B-1.1-HF [Fastest] 2 TheBloke/Wizard-Vicuna-13B-Uncensored-HF 3 NousResearch/Nous-Hermes-13b [Recommand] 4 TheBloke/guanaco-65B-HF [Biggest]

maxchiron

Any HuggingFace Model means, Could I use "mosaicml/mpt-7b-storywriter" model as well with this?

2

Any HuggingFace Model means, Could I use "mosaicml/mpt-7b-storywriter" model as well with this? Is there any restrictions on the nature of these models? The YouTube @PromtEngineer mentioned this "localGPT" could...

ashokrs

GPU not utilized

2

Hi, i am running with 3090 but it seems still it uses CPU. in the log i see "Running on: cuda" but examining the resource usage the GPU is almost...

stavsap

Main 1

1

Devesh-N

Add only new documents when re-ingesting + add progress bar for ingest process

1

Dear dev, Would be great if you could add 2 new features, similar to privateGPT: 1) When I run the ingest process, only new files should be added to the...

janhp

rahulb7230

Currently, all files are loaded in a single thread. This PR, based on [this article](https://superfastpython.com/multithreaded-file-loading/#Load_Files_Concurrently_With_Processes_and_Threads_in_Batch), will allow loading the documents in multiple threads which speeds up the process when having...

Tchekda

Getting "AssertionError: Torch not compiled with CUDA enabled"

8

Then the program ends. Ideas?

shecky2000