apcameron
apcameron
Please Add Support for quantized (4-bit) Models so we can run models similar to llama.cpp and alpaca.cpp that only require 4GB of GPU memory
Having a Progress Bar or the percentage displayed would be helpful on injest.py
Copy ggml-opencl.cpp from llama.cpp Update CMakefiles.txt This addresses the following https://github.com/ggerganov/ggml/issues/216 and https://github.com/ggerganov/ggml/issues/205
[ 1%] Building C object src/CMakeFiles/ggml.dir/ggml.c.o /home/andrew/Downloads/ggml/src/ggml.c: In function ‘quantize_row_q8_0’: /home/andrew/Downloads/ggml/src/ggml.c:1026:15: warning: unused variable ‘nb’ [-Wunused-variable] 1026 | const int nb = k / QK8_0; | ^~ /home/andrew/Downloads/ggml/src/ggml.c: In function...
There is no code2prompt_no_modal.py for those of us who do not want to use Modal
I am trying to use alternatives to openai One alternative is to use https://github.com/go-skynet/LocalAI Another is to use llama.cpp with the python API plugin which I have partially working. I...
[ERROR]: Unknown Intel device id: 0x22B0 Please, create a new issue with this error message on https://github.com/Dr-Noob/gpufetch/issues [ERROR]: No GPU was detected! Available GPUs are: - GPU 0: * Vendor:...
Can this be used with Pytorch 2.0 and greater and if so what is the process to use it. This is what I see when I try to build it....
Add Support for https://huggingface.co/ise-uiuc/Magicoder-S-DS-6.7B The convert.py script fails on this model and the GGUF provided by The Bloke does not work with your code.
Please consider adding support for GROK-1 https://x.ai/blog/grok-os https://huggingface.co/xai-org/grok-1