Could not get any usable output from it for any real usecase.
Can't see any real value in using 1 bit llms except and apart for the sake of running it for demo or feel good factor of running a higher param model locally and in limited hardware!
Since use as it is very limited, could someone throw some light on any actual use case?
Pretty sure this might be a duplicate. Regardless, tried the 1bit bonsai 27b gguf three different ways - their llama.cpp fork (prism, was it) on 2 machines (1255u/16g, m5 max/128g) and the web (on the 1255u). With llama.cpp it works. on the web it emits the same thing over and over. Prompt was "do you see anything wrong with this code: <C code, compound literal passed as a pointer to a function in an if statement>", result was literally "Yes, let'ssomestruct_struct_tsomestruct<a bit of similar garbage>structstructstruct<forever>.
Locally, it's definitely not the full 3.6 27b, but for ~6G with the context, it's quite impressive, and I like what this implies for larger models. Speeds on the 1255u are abysmal, though (~1TPS or less) - granted, CPU-only.
I tried the smallest ome, the only available, and got an error:
```
Could not load.
Error: failed to call OrtRun(). ERROR_CODE: 1, ERROR_MESSAGE: Non-zero status code returned while running GroupQueryAttention node.
Name:'/model/layers.0/attn/GroupQueryAttention' Status Message: Failed to create a WebGPU compute pipeline: A valid external Instance reference no longer exists.
```
> pasteurization is a, which a, the which which is, the and process, the the past, the and the, and and and past, and past, and and and and the, the and past, process is the is is is is, and the, past, and and future, process, and and and and and and and the, past, process, process, the the, the the, is and the, the the, and and and, and process, and and the, past, and and and past, and the, the, and the past, the the, process, process, and past, the past, past, the and, the past, and and and and and and and and and the, and and and and and and and, the the, the the, the or and and, the the, the and the, which the, and the, the the, past, and n the process, and and and and, past, and, and and, the past, and, the the, past,, and the, the the, the is the, past, and and and and and, and and and past, the and the, the the, the the, are and past, and which the, the and n, n the, the n past, past, n the, and n, the the process, which past, the the, the n, the the, the is past, the the, is, past, the the, past, and past, process, the the, the the, the and and the, and which past, the
(and that basically just goes on and on like that)
I run Bonsai-27B Q1_0 on my Android phone via the PocketPal app. It's slow but good. I wouldn't want to run fewer B. By any measure, my phone has less memory than my laptop browser.
Impressive, I asked it how many r's in strawberry and it was immediately wrong with 2. any further questions I asked it proceeded to re-explain why there were 2 r's in strawberry, despite asking the silly "walk or drive to get my car washed" question. I struggle to see what these sorts of models could possibly be good at.
18 comments
[ 5.2 ms ] story [ 49.3 ms ] thread1. https://github.com/stfurkan/bitgpu
2. https://aidekin.com --> this is one of my projects that's currently using bitgpu engine
> I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Ref: https://opper.ai/blog/car-wash-test
Can't see any real value in using 1 bit llms except and apart for the sake of running it for demo or feel good factor of running a higher param model locally and in limited hardware!
Since use as it is very limited, could someone throw some light on any actual use case?
Locally, it's definitely not the full 3.6 27b, but for ~6G with the context, it's quite impressive, and I like what this implies for larger models. Speeds on the 1255u are abysmal, though (~1TPS or less) - granted, CPU-only.
``` Could not load.
Error: failed to call OrtRun(). ERROR_CODE: 1, ERROR_MESSAGE: Non-zero status code returned while running GroupQueryAttention node. Name:'/model/layers.0/attn/GroupQueryAttention' Status Message: Failed to create a WebGPU compute pipeline: A valid external Instance reference no longer exists. ```
Me:
> Describe the process of pasteurisation
Response:
> pasteurization is a, which a, the which which is, the and process, the the past, the and the, and and and past, and past, and and and and the, the and past, process is the is is is is, and the, past, and and future, process, and and and and and and and the, past, process, process, the the, the the, is and the, the the, and and and, and process, and and the, past, and and and past, and the, the, and the past, the the, process, process, and past, the past, past, the and, the past, and and and and and and and and and the, and and and and and and and, the the, the the, the or and and, the the, the and the, which the, and the, the the, past, and n the process, and and and and, past, and, and and, the past, and, the the, past,, and the, the the, the is the, past, and and and and and, and and and past, the and the, the the, the the, are and past, and which the, the and n, n the, the n past, past, n the, and n, the the process, which past, the the, the n, the the, the is past, the the, is, past, the the, past, and past, process, the the, the the, the and and the, and which past, the
(and that basically just goes on and on like that)
My demo uses 2 bit quantization to run llama3 models on any device with enough ram.
https://galqiwi.github.io/aqlm-rs/