Andrew Falgout

-f option seems to not work

3

It either doesn't work for importing a prompt, or I don't know what the file format is suppose to be. I put this in a file. My name is Greg.\...

python privateGPT.py : core dumping

5

draeician@vivy:~/git/privateGPT$ python3 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...

[FEAT]

1

**Describe the solution you'd like** This should be a pretty easy request. Add the ability to have a logging area to log chats, perhaps create a directory in the logging...

[Bug] Custom Preset for Watch ENco

12

### Current Behavior I created a preset, that I verified works by using it manually called "General/Fast1080p30h265". I just took the regular one of that name, and checked the h265...

Illegal instruction (core dumped)

4

### .env # Generic TEXT_EMBEDDINGS_MODEL=sentence-transformers/all-MiniLM-L6-v2 TEXT_EMBEDDINGS_MODEL_TYPE=HF # LlamaCpp or HF USE_MLOCK=false # Ingestion PERSIST_DIRECTORY=db DOCUMENTS_DIRECTORY=source_documents INGEST_CHUNK_SIZE=500 INGEST_CHUNK_OVERLAP=50 INGEST_N_THREADS=3 # Generation MODEL_TYPE=LlamaCpp # GPT4All or LlamaCpp MODEL_PATH=eachadea/ggml-vicuna-7b-1.1/ggml-vic7b-q5_1.bin MODEL_TEMP=0.8 MODEL_N_CTX=1024 # Max...

fresh build, page loads but working icon in the middle never finishes

41

**Describe the bug** I did a fresh docker build, got to localhost:3000, and the page never finishes loading. I get the icons on the left side, and a swirling circle...

Added persistent env file for the server, so one update to /etc/default/ollama will stay between updates.

git push failed : cannot read username or password

2

I didn't get prompted for a username or password. I did on my windows system, but on my linux system it never prompted. This is running on Linux Mint 20.3,...

core dump when loading model

2

## Expected Behavior I downloaded the Wizard-Vicuna-7B-Uncensored.ggmlv3.q2_K., and clicking it in the model farm to load it. ## Current Behavior I click the model, and I get a core dump....

It will update the ollama.service to use an env file. It will create a default /etc/default/ollama if it doesn't already exist.