private-gpt issues

> ~/dev/privateGPT$ python ingest.py

7

> **~/dev/privateGPT$ python ingest.py** > > ``` > Traceback (most recent call last): > File "/home/sharan/dev/privateGPT/ingest.py", line 7, in > from constants import CHROMA_SETTINGS > File "/home/sharan/dev/privateGPT/constants.py", line 11, in...

omerta222

What are the requirements on hardware for run this project?

4

Can you help giving more information about the requirements in hardware to test this project particular what I need to in terms of hardware: > Instructions for ingesting your own...

pabl-o-ce

ADD UI Chat simple

16

Thanks @imartinez for great repo about private data and LLM offline. - Make the conservation of chat - Can edit prompt for instruction - Can edit config model, number context...

vnk8071

GGML_ASSERT: /project/ggml/src/ggml.c:3732: ctx->mem_buffer != NULL Aborted

3

python privateGPT.py llama.cpp: loading model from models/ggml-model-q4_0.bin llama.cpp: can't use mmap because tensors are not aligned; convert to new format to avoid this llama_model_load_internal: format = 'ggml' (old version with...

hanwsf

how can i use gpu to run?

11

I use windows , use cpu to run is to slow

ajavaer

I am going back

1

Yeah

omerta222

Does anyone success run on new update ?

1

is anyone run successful with newly update version?

rexzhang2023

I also build a private GPT project use vicuna-13b, it can connect local database.

4

I build a private GPT project, It can deploy locally, and you can use it connect your private environment database and handler your data. The project is there: https://github.com/csunny/DB-GPT

csunny