-
I try to test the XNLI results using the latest commit. And I find the inputs have a prefix_token which looks like:
```
[(('', ' 他说，妈妈，我回来了。, 正确? 是的, 校车把他放下后，他立即给他妈妈打了电话。'), [1], [55363, 2296, 55361…
-
First, thanks for this work. Providing open source SAEs for a model like Llama is a huge boon to the community.
I'm working on a simple script to use your `generate_description` function to assign …
-
When I'm running phi-2 on device there is a issue while generating the responses. When I feed it a question it starts generating the response(although quite slow) but it just doesn't stop.
In ChatVi…
-
-
I am trying to finetune Llama 3.1 with below settings
Unsloth 2024.8: Fast Llama patching. Transformers = 4.44.2.
GPU: NVIDIA A10G. Max memory: 21.988 GB. Platform = Linux.
Pytorch: 2.1.0+cu118. CU…
-
I got unsloth running in native windows, (no wsl). You need visual studio 2022 c++ compiler, triton, and deepspeed. I have a full tutorial on installing it, I would write it all here but I’m on mobile…
-
Hiya Ciaran!
I received this message (below) when I tried to change the category for 'Greenhouse gas emissions for 55 African countries'.
I am also struggling to change the categories of 'Covid-…
-
zodat ik mijn applicatielandschap flexibel(er) kan inrichten en registratiecomponenten zowel voor ZGW als voor niet-ZGW kan gebruiken.
Dit geldt i.i.g. voor DRC en BRC die ook buiten ZGW een rol zu…
-
Hello!
I have used diamond to obtain hits with public databases and then filtered my data using Blobtools. I have used the commands specified on your webpage (https://blobtoolkit.genomehubs.org/blo…
-
### Description of the bug:
Hi @pkgoogle ,
i used example c++ code to inference model i transfer, it can show some error.
- my command
```
bazel run -c opt //ai_edge_torch/generative/example…