-
### When did you clone our code?
I cloned the code base after 5/1/23
### Describe the issue
Issue:
When I fine-tuned the whole network with Chinese data, which is step 3 of the training scri…
-
When using `vast.ai` and image `nvidia/cuda:12.3.1-devel-ubuntu22.04`
and 4x RTX3090 on a AMD EPYC 7302P 16-Core Processor,
Trying any "small model" ( i have not tried large models yet )
I get…
-
### Feature Description
An example on using llava-13b and llamaindex would be great, Here is the model available on [replicate](https://replicate.com/yorickvp/llava-13b/)
### Reason
_No response_
…
-
Hello, i am having a problem using LLava via Server.
server launch command
```
export PYTHONPATH=$PYTHONPATH:`pwd`
export CUDA_VISIBLE_DEVICES=4,5,6,7
./server -m models/llava/ggml-model-q4_k.g…
-
Had to go code diving to work out what --model-type was meant to be. Can we please have the docs for the command line parameters in an appropriate place in the wiki?
-
### Question
excuse me，I would like to ask you that why I get the following error when pretraining v1.5，My code is: ./scripts/v1_5/pretrain.sh
output：
[2023-10-21 19:41:04,065] [INFO] [real_acceler…
-
### Question
Hi, I'm trying to pretrain using xformer but I'm getting an omm error, do you know the solution?
here is my script code and log
Thank you
```
PROMPT_VERSION=plain
########### DO N…
-
# I was told to come here by this other dude:
https://github.com/trzy/llava-cpp-server/issues/3#event-10687266750
ISSUE: when I give non-existant file names, it segfaults #3
these files do…
-
I am running docker on windows 11, running ubuntu22 inside docker.
``` bash
python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 60000 --worker http://localho…
-
Hi,
First of all thanks for the project, I love it. The Llava model works well for me, but I think I'm doing something wrong with Mistral and when trying to use GGUF models.
I'm trying to get it…