-
Tried to convert `https://huggingface.co/intfloat/e5-large-v2` to ggml with the current `d9f04e609fb7f7e5fb3b20a77d4d685219971009` commit. However, execution of the converted f32, f16, q4_0, and q4_1 …
-
### Motivation and description
See here:
https://github.com/ggerganov/ggml/pull/254/files
I think we may need QuickGELU, for compatibility, if not same as GELU, more than just optimization.
…
-
I have a suggestion.
Just found this project [https://github.com/guinmoon/LLMFarm](url).
Just an FYI, GGUF models work with it, I am not sure if GGML does.
-
Following the instructions to use docker compose, I get several error(s) on docker compose run:
- [Error: EXDEV: cross-device link not permitted, rename '/root/dalai/alpaca/models' -> '/root/dalai/tm…
-
Hi !
I quantized the 13B model, I got a 15,15Go file. But I got an error when I try to mount it with ./main
`main: seed = 1681070012
llama_model_load: loading model from '/content/vigogne/llama…
-
### What is the issue?
6月 11 01:17:54 Venue-vPro ollama[2760]: time=2024-06-11T01:17:54.332+08:00 level=INFO source=server.go:567 msg="waiting for server to become available" status="ll>
6月 11 01:17…
-
### What is the issue?
qwen2:72b-instruct-q4_K_M produces gibberish output:
```
>>> hello.
#:G*:^C
```
Other models in other quantizations work correctly.
Ollama server output:
```
$ …
-
Hie 👋🏻
Coming from [this](https://github.com/ggerganov/ggml/blob/master/examples/gpt-j/convert-h5-to-ggml.py) GGML conversion script and the issue that you commented in https://github.com/ggerganov/…
-
I tried compiling and running the pre made one. I have i7 windows 11 pro with 16 gb ram. It stops and goes back to command prompt after this:
main: seed = 1679872006
llama_model_load: loading mo…
-
I use `SD_METAL=ON` to build `sd.cpp` on m1. However, the generated image seems to be blured or tends to be in the cartoon-like style. This happens on all models (v2, SDXL, SDXL turbo). This problem o…
Ucag updated
7 months ago