-
### Environment
If applicable, please include the following:
**CPU architecture:** x86_64
**CPU/Host memory size:** 440 GiB memory
### GPU properties
GPU name: A100
GPU memory size: 160G…
-
I encountered an error while trying to merge two Qwen-based lora models using a mixture of experts (MoE) configuration with qwen architecture. I’m working with a phi2_moe2.yml configuration file, but …
-
### Expected behavior
The following code
```
dev1 = qml.device("lightning.qubit", wires=1)
@qml.qnode(dev1)
def circuit2(phi1, phi2):
qml.RX(phi1, wires=0)
qml.RY(phi2, wires=0)
…
-
I’m not sure what all would be involved, but something that’s making waves is “self extend”, where it seems to be possible to make models work at larger context sizes than what they were originally de…
-
### System Info
```shell
* optimum: 1.16.1
* Windows amd64
* Python 3.8.18
* onnxruntime nightly build
* onnx 1.15.0
* protobuf 3.20.3
* torch 2.1.2
```
### Who can help?
_No resp…
-
I don't see if there is any WebGPU support in the wasm examples for Phi2
Thank you.
-
Following what was done in #689 we need an implementation of the cylindrical and spherical versions of
- [ ] TotalVolume
- [ ] TotalSurface
- [ ] AverageVolume #820
- [ ] AverageSurface #820
…
-
I am running mistral 7b and phi 2 in ARC GPU and getting a core dump error.
I have converted the model into lower precision (int4) and saved it. And then loading the int4 model in the GPU.
The sa…
-
Hey there! Had an issue a few months ago about not being able to quantize the model in order to run it using ollama.
Figured it out back then and all was good.
Today I wanted to train a differen…
-
I have a strange issue on my C64C. Everything loads perfectly except for any games from $olo1870.
In the OneLoad64 collection, the majority of the EasyFlash mutliload games are from a dev call $olo1…