-
Current implementation of linux_train on cpu fine-tuning is (almost) unsable.
Another method: [Finetune LoRA on CPU using llama.cpp](https://rentry.org/cpu-lora)
-
Hi,
I've trying to serve different Phi3 models using the Llama.cpp server that is created by the init-llama-cpp ipex.
When I server with this version I have two problems:
1) The server doesn…
hvico updated
2 months ago
-
This was a problem that I think was prematurely `closed`:
https://github.com/abetlen/llama-cpp-python/issues/1166
My current efforts are to get a llama 3.1 70B gguf running on 2 3090s, and no ma…
-
I just installed llama-cpp-2 on Windows and when tried to build it failed with error.
_Error_
```console
cargo build -p llama-cpp-2
Compiling windows_x86_64_msvc v0.52.6
Compiling windows…
-
Hi there,
I wanted to try out your GUI with a Docker build (cuda backend).
I ran into a couple of issues while building the image:
1. could not install pyenv and python due to an issue with the e…
-
I ran the tests below on a Macbook Pro with m3-max 64GB. MLX seems to run much slower than llama.cpp with flash attention enabled.
Is this speed just a result of flash attention not available in M…
-
tried to compile the routines unsuccefully
would you please hlp ?
(bitnet-cpp) triumph@triumph-HP-Z6-G5-Workstation-Desktop-PC:~/github/BitNet/src$ $CC
aarch64-ostl-linux-gcc: fatal error: no input …
-
### Description
Have tried a number of huggingface models and consistently get the error message:
llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 292, …
-
i am installing llama-cpp-python for privategpt, after following the instructions i was getting few errors one of the error was privategpt requires llama-cpp-python at several process
so I started i…
-
In llama model, [there has an input varation](https://github.com/tenstorrent/pytorch2.0_ttnn/blob/196ae752825cab6c532fa8ed741f3acd030385a3/tests/autogen_op/Llama/test_Llama_aten_unsqueeze_default.py#L…